© 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 · 40026 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
40026

INDEX

Explanations

ization

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

iser

-0.50

isers

-0.45

 dampak

-0.45

IST

-0.45

ной

-0.43

illiard

-0.41

-0.41

top

-0.41

-0.41

 съ

-0.41

POSITIVE LOGITS



0.99

#+#

0.95

webElementXpaths

0.94

 تضيفلها

0.93

ⓧ

0.93

 ſind

0.91

ViewFeatures

0.88

 BoxFit

0.88

 Мексичка

0.85

ImageContext

0.85

Activations Density 0.187%

No Known Activations