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. 22-CLT-HP
    4. 74488
    Prev
    Next
    INDEX
    Explanations

    Code, programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.89
    expandindo
    -0.62
     незавершена
    -0.62
     NUKAT
    -0.59
     jspb
    -0.58
     ویکی‌پدی
    -0.57
     المعيارى
    -0.56
    цездатний
    -0.56
    contentLoaded
    -0.56
     跳转至
    -0.55
    POSITIVE LOGITS
     lower
    0.94
    lower
    0.75
    Lower
    0.65
     higher
    0.62
     Lower
    0.59
     LOWER
    0.56
     even
    0.56
    LOWER
    0.52
    جغرافيا
    0.48
    RunAsync
    0.47
    Activations Density 0.014%

    No Known Activations