INDEX

Explanations

the letter "m" when it is part of a technical term or acronym

oai_token-act-pair · gemini-2.0-flash

m

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

gtest

-0.51

urlpatterns

-0.50

-0.48

UObject

-0.46

urando

-0.46

פ

-0.45

lacian

-0.45

بغ

-0.44

LEIA

-0.43

Autoritní

-0.43

POSITIVE LOGITS

DockStyle

0.85

protoimpl

0.71

 CreateTagHelper

0.70

RenderAtEndOf

0.68

RegistryLite

0.68

 betweenstory

0.64

ніципалі

0.64

 تانيه

0.64

 propOrder

0.64

AccessorTable

0.62

Activations Density 0.358%

the letter "m" when it is part of a technical term or acronym

m

No Comments

No Known Activations