INDEX

Explanations

code-related elements and structures within the text

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

Code, URLs, and names

np_acts-logits-general · gemini-2.0-flash

angular @inject NgFor molecules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

sizeCache

-0.55

ChromeDriver

-0.55

openzeppelin

-0.53

DoubleQuotes

-0.52

igure

-0.51

orghini

-0.51

.*")]

-0.51

ochlor

-0.50

 setw

-0.49

ISupport

-0.49

POSITIVE LOGITS

NgModule

0.56

 autorytatywna

0.52

 Injector

0.49

 للاسماء

0.48

 Reflective

0.48

 صوتيه

0.47

 Host

0.47

 Change

0.46

 Deutscher

0.46

host

0.46

Activations Density 0.169%

code-related elements and structures within the text

Code, URLs, and names

angular @inject NgFor molecules

No Comments

No Known Activations