© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16734
    Prev
    Next
    INDEX
    Explanations

    expressions of writing style and language use

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.67
    tahui
    -0.65
    unnitel
    -0.64
    MLLoader
    -0.60
     utafitiHapana
    -0.53
    olyb
    -0.53
    eschouwers
    -0.52
    Sized
    -0.51
     muslin
    -0.51
    eterangan
    -0.50
    POSITIVE LOGITS
     Language
    0.65
     language
    0.65
     linguaggio
    0.63
     jargon
    0.60
     expressions
    0.58
    ViewImports
    0.58
     LANGUAGE
    0.57
     ExecuteAsync
    0.56
     words
    0.56
    poken
    0.56
    Activations Density 0.112%

    No Known Activations