© 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 · 45448 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45448

INDEX

Explanations

hig

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

maid

-1.24

 Monfieur

-0.99

 Forumite

-0.94

RectangleBorder

-0.93

 Normdatei

-0.93

 Majefty

-0.91

 CreateTagHelper

-0.89

Efq

-0.89

 iſt

-0.86

 Reſ

-0.86

POSITIVE LOGITS

↵

0.51

↵↵

0.50

thea

0.48

0.48

لف

0.47

0.47

fini

0.47

0.47

ri

0.46

<h3>

0.46

Activations Density 1.658%

No Known Activations