© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 97552 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
97552

INDEX

Explanations

part

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

 Part

-1.09

Part

-0.87

 Bill

-0.73

Ad

-0.56

 PART

-0.56

googleapis

-0.52

Bill

-0.49

กัน

-0.48

Par

-0.47

AD

-0.46

POSITIVE LOGITS

 Monfieur

0.97

 myſelf

0.95

 Theſe

0.94

 itſelf

0.94

 Anſ

0.90

 himſelf

0.89

 Jefus

0.86

 purpoſe

0.85

 houſe

0.84

 Majefty

0.84

Activations Density 1.648%

No Known Activations