INDEX

Explanations

words related to creating websites or web applications

oai_token-act-pair · gemini-2.0-flash

WordPress/Magento/PHP

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

RenderAtEndOf

-0.79

AnimationsModule

-0.62

########.

-0.59

riwal

-0.50

Smell

-0.47

 sociais

-0.47

BeginContext

-0.47

AutoresizingMask

-0.47

 utafitiHapana

-0.46

paksa

-0.46

POSITIVE LOGITS

 Apps

0.63

وصلات

0.58

rsiniz

0.57

Apps

0.56

 Applications

0.54

<",

0.54

شكرا

0.53

 Gulch

0.52

 apps

0.51

 Programming

0.51

Activations Density 6.170%

words related to creating websites or web applications

WordPress/Magento/PHP

No Comments

No Known Activations