INDEX

Explanations

This neuron seems to activate on code snippets and mathematical expressions, particularly those involving variable assignments or function calls, sometimes with the word "lol".

oai_token-act-pair · gemini-2.0-flash

say ending parenthesis

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.88

 CreateTagHelper

-0.79

EDEFAULT

-0.78

RenderAtEndOf

-0.69

ModelSerializer

-0.69

Datuak

-0.68

 Италијани

-0.67

 propOrder

-0.66

resave

-0.64

WebElementEntity

-0.63

POSITIVE LOGITS

ora

0.57

bukkit

0.47

oras

0.45

ūra

0.44

pédie

0.42

MLLoader

0.42

labelledby

0.41

 SUBJECT

0.41

elds

0.41

 Journal

0.41

Activations Density 1.835%

This neuron seems to activate on code snippets and mathematical expressions, particularly those involving variable assignments or function calls, sometimes with the word "lol".

say ending parenthesis

No Comments

No Known Activations

This neuron seems to activate on code snippets and mathematical expressions, particularly those involving variable assignments or function calls, sometimes with the word "lol".

say ending parenthesis

No Comments

No Known Activations