© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 20-CLT-HP · 75797 ｜ Neuronpedia

Home
Gemma-2-2B
20-CLT-HP
75797

INDEX

Explanations

couch

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 okuyayım

-0.69

-0.59

 ModelExpression

-0.53

 Spéc

-0.51

Ifc

-0.50

Representation

-0.50

nelse

-0.50

yaf

-0.49

myra

-0.48

сылкі

-0.47

POSITIVE LOGITS

حوالہ

0.55

GIVEREF

0.52

stands

0.52

hy

0.51

ob

0.49

hyr

0.49

liothèque

0.48

hogy

0.48

 متعلقه

0.47

 lilla

0.47

Activations Density 0.001%

No Known Activations