© 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 · 45310 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45310

INDEX

Explanations

copyright

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

 تانيه

-1.04

 myſelf

-0.99

 Majefty

-0.94

 Económica

-0.88

 deſt

-0.87

 colère

-0.87

 themſelves

-0.86

 cdti

-0.85

DockStyle

-0.84

 Monfieur

-0.83

POSITIVE LOGITS

ing

1.06

ING

0.67

️

0.66

0.64

per

0.60

la

0.60

Ad

0.59

‘

0.58

ering

0.57

of

0.57

Activations Density 0.093%

No Known Activations