INDEX

Explanations

words and phrases related to email and computer usage for communication

oai_token-act-pair · gemini-2.0-flash

email

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 utafitiHapana

-0.69

 uVar

-0.63

 textStatus

-0.62

ditor

-0.61

didSet

-0.60

 endregion

-0.60

=$((

-0.59

ientôt

-0.59

^(@)

-0.57

glGen

-0.57

POSITIVE LOGITS

+#+

0.60

InjectAttribute

0.54

 חיצוניים

0.52

IContainer

0.50

onom

0.50

er

0.48

 &___

0.47

NamedQuery

0.45

tagHelperRunner

0.45

MergeFrom

0.45

Activations Density 3.528%

words and phrases related to email and computer usage for communication

email

No Comments

No Known Activations