© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 41089 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
41089

INDEX

Explanations

learn

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

 learn

-1.39

 learns

-1.16

 EconPapers

-1.15

 greateſt

-1.15

MigrationBuilder

-1.14

 Roskov

-1.12

expandindo

-1.10

 Theſe

-1.10

 myſelf

-1.10

 purpoſe

-1.08

POSITIVE LOGITS

 more

0.77

in

0.74

0.74

 from

0.68

of

0.67

not

0.66

0.65

for

0.65

0.64

0.64

Activations Density 0.013%

No Known Activations