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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    reference

    np_max-act · 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
    GetAxis
    -0.44
     lip
    -0.42
     ref
    -0.38
    resizing
    -0.38
    posis
    -0.38
    Czytaj
    -0.37
     نفت
    -0.37
     postoperative
    -0.36
     opinion
    -0.36
     sẻ
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.96
    ftagPool
    0.73
    IsMutable
    0.71
     AttributeSet
    0.67
     resourceCulture
    0.65
    ../../../
    0.61
     $__
    0.60
     ویکی‌پدی
    0.59
     *)__
    0.58
     للاسماء
    0.58
    Activations Density 0.054%

    No Known Activations