© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-2-2B · 1-CLT-HP · 8807 ｜ Neuronpedia

Home
Gemma-2-2B
1-CLT-HP
8807

INDEX

Explanations

ta

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

Negative Logits

ta

-1.25

TA

-0.69

ta

-0.61

 vPvB

-0.54

Ta

-0.53

sit

-0.53

-0.51

Ta

-0.49

ite

-0.48

TA

-0.48

POSITIVE LOGITS

OGND

0.80

annica

0.69

 الحره

0.68



0.67

 autorytatywna

0.66

AnchorStyles

0.63

ględ

0.63

tvguidetime

0.63

 Audiodateien

0.61

省市镇

0.61

Activations Density 0.015%

No Known Activations