© 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 · 0-CLT-HP · 92834 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
92834

INDEX

Explanations

Tw

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

Mes

-0.54

TW

-0.54

Bl

-0.53

Tw

-0.53

bl

-0.53

on

-0.51

Tw

-0.51

dim

-0.50

face

-0.49

cap

-0.48

POSITIVE LOGITS

 pleaſure

0.80

 reaſon

0.73

 cauſe

0.72

 avoient

0.72

 perspiration

0.68

 purpoſe

0.68

 ſte

0.67

 uſed

0.67

 fubject

0.67

ſelf

0.66

Activations Density 0.112%

No Known Activations