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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14162
    Prev
    Next
    INDEX
    Explanations

    the word "for" (case-insensitively) and abbreviations that have "FOR" in them

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    InputBorder
    -0.62
    gdx
    -0.55
    pls
    -0.50
    picasso
    -0.48
     taught
    -0.48
    til
    -0.48
    ocin
    -0.47
    QRCode
    -0.47
     Evangelio
    -0.47
    řeba
    -0.46
    POSITIVE LOGITS
    devamını
    0.72
     transférez
    0.64
     समीक्षाओं
    0.61
    addPreferredGap
    0.61
    Spoljašnje
    0.59
    )";
    
    0.58
    CreateModel
    0.56
    TagMode
    0.56
    };*/
    0.56
    )");
    
    0.55
    Activations Density 0.735%

    No Known Activations