© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 94997 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
94997

INDEX

Explanations

legal documents

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

URBANA

-0.61

Autoritní

-0.56

roek

-0.55

 للتو

-0.54

 lenker

-0.53

 Audiodateien

-0.51

ClientRect

-0.50

-0.49

bkz

-0.48

ZZLE

-0.48

POSITIVE LOGITS

0.63

StructEnd

0.56

EObject

0.53

 περί

0.53

bcryptjs

0.53

httphttps

0.50

ampung

0.50

ėd

0.50

+:+

0.49

0.48

Activations Density 0.375%

No Known Activations