© 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 · 45254 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45254

INDEX

Explanations

about

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

-0.78

”

-0.60

 About

-0.60

’

-0.59

About

-0.55

”.

-0.54

.”

-0.53

-0.53

<bos>

-0.52

-0.52

POSITIVE LOGITS

 myſelf

0.85

 Monfieur

0.82

 itſelf

0.77

 themſelves

0.77

 Majefty

0.76

 ſeveral

0.75

 pleaſure

0.74

ieteur

0.73

 neceffary

0.71

 purpoſe

0.67

Activations Density 0.027%

No Known Activations