Entities · Models
Gemma 2-2B-it
4 articles tagged with this entity.
-
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
-
Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
-
BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
-
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs