INDEX

Explanations

This neuron seems to activate on a diverse set of topics, like processes in the body, reactions to DDT, technical code implementation, magnetism and Jackson family legal disputes

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.59

GenerationType

-0.56

 betweenstory

-0.55

 internetowa

-0.52

 Privilege

-0.48

 оригіналу

-0.48

Cyfeiriadau

-0.47

>>()

-0.47

ManagedBean

-0.46

leville

-0.46

POSITIVE LOGITS

IContainer

0.64

DrawerToggle

0.57

 AppCompatTheme

0.54

GraphicsUnit

0.53

TagHelpers

0.51

 puissiez

0.50

bootstrapcdn

0.50

DispatchToProps

0.49

dafx

0.49

évaluateur

0.49

Activations Density 1.843%

This neuron seems to activate on a diverse set of topics, like processes in the body, reactions to DDT, technical code implementation, magnetism and Jackson family legal disputes

No Comments

No Known Activations