INDEX

Explanations

this neuron looks for HTML code, numbers, and some words (craft, new, click)

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

setVerticalGroup

-0.80

 متعلقه

-0.71

richTextPanel

-0.70

WriteBarrier

-0.68

BeginInit

-0.57

̀ng

-0.56

CodedInputStream

-0.55

 ProtoMessage

-0.55

InvalidProtocol

-0.55

XmlAccessorType

-0.55

POSITIVE LOGITS

orp

0.50

Magn

0.44

ksom

0.44

 Magn

0.43

roga

0.42

jš

0.42

tschaft

0.41

ership

0.40

 suis

0.40

Numerology

0.40

Activations Density 0.202%

this neuron looks for HTML code, numbers, and some words (craft, new, click)

No Comments

No Known Activations