INDEX

Explanations

The neuron identifies expressions of gratitude.

oai_token-act-pair · gemini-2.0-flash

thank

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 thanks

-2.42

thanks

-2.06

 thank

-2.02

 THANKS

-1.78

 Thanks

-1.78

 gracias

-1.73

Thanks

-1.66

thank

-1.60

 grazie

-1.53

 graças

-1.44

POSITIVE LOGITS

Chham

0.60

MENAFN

0.57

styleUrls

0.57

MessageTagHelper

0.56

uevos

0.55

migrationBuilder

0.54

 AssemblyTitle

0.54

simpleType

0.54

}{*}{}

0.53

parsedMessage

0.53

Activations Density 1.300%

The neuron identifies expressions of gratitude.

thank

No Comments

No Known Activations