Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11068
    Prev
    Next
    INDEX
    Explanations

    references to playing or reviewing video games

    oai_token-act-pair · gemini-2.0-flash

    programming language constructs or methods

    np_token-act-pair-logits · gpt-4o-mini

    Code related tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <em>
    -0.59
    <i>
    -0.54
     
    -0.51
    (
    -0.40
    .
    -0.40
     in
    -0.40
    oper
    -0.39
     $
    -0.39
     `
    -0.38
    <eos>
    -0.38
    POSITIVE LOGITS
    SharedCtor
    1.20
     CreateTagHelper
    1.09
    DeleteBehavior
    1.04
     itſelf
    1.02
    ſelf
    0.96
     propOrder
    0.95
     تضيفلها
    0.93
     дописавши
    0.93
     myſelf
    0.92
    !*\
    0.89
    Activations Density 0.983%

    No Known Activations