INDEX

Explanations

industry

np_token-act-pair-logits · gemini-2.0-flash

industry

np_max-act-logits · gemini-2.0-flash

words relating to business, industry, organizations, and market sectors

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

apunov

-0.68

GEBURTSDATUM

-0.68

SupportActionBar

-0.61

Népesség

-0.57

IBOutlet

-0.56

Билгалдахарш

-0.56

makeText

-0.56

 }}"></

-0.54

}}^{(

-0.53

NewUrlParser

-0.52

POSITIVE LOGITS

 proverbs

0.57

 atheists

0.52

ArrayAdapter

0.51

 Compose

0.51

 ArrayAdapter

0.50

 transfé

0.50

 Elemental

0.50

 cardinality

0.49

seamnă

0.49

 aliens

0.48

Activations Density 2.326%

industry

industry

words relating to business, industry, organizations, and market sectors

No Comments

No Known Activations