© 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 · 1-CLT-HP · 10949 ｜ Neuronpedia

Home
Gemma-2-2B
1-CLT-HP
10949

INDEX

Explanations

vey

np_max-act · 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

vey

-1.74

VEY

-1.27

DockStyle

-0.93

veys

-0.93

ViewFeatures

-0.90

rrggbb

-0.88

 getItemId

-0.82

veyor

-0.81

ConstraintMaker

-0.79

 pinulongan

-0.77

POSITIVE LOGITS

 laws

0.49

0.48

ri

0.48

ra

0.46

tiz

0.45

 extra

0.44

ac

0.43

 courts

0.43

ci

0.43

otts

0.43

Activations Density 0.011%

No Known Activations