INDEX

Explanations

programming concepts related to data structures and methods

oai_token-act-pair · gpt-4o-mini Triggered by @bot

list of items

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reverso

-0.63

rdquo

-0.53

MEP

-0.52

uterte

-0.51

Zer

-0.49

 poch

-0.49

androidx

-0.49

-0.48

ChildIndex

-0.48

echi

-0.48

POSITIVE LOGITS

GraphicsUnit

0.65

routeProvider

0.60

 ejerc

0.57

 habet

0.55

addGap

0.55

 EdgeInsets

0.55

 UIFont

0.54

smithy

0.54

IntoConstraints

0.53

XmlAccessType

0.53

Activations Density 0.044%

programming concepts related to data structures and methods

list of items

No Comments

No Known Activations