© 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. 5-CLT-HP
    7. 5319
    Prev
    Next
    INDEX
    Explanations

    to

    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
    <eos>
    -0.49
    ян
    -0.46
    LEAR
    -0.46
     Fright
    -0.45
    الثة
    -0.43
     thống
    -0.43
     Reviewed
    -0.42
     tarik
    -0.42
    </sub>
    -0.42
     reak
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.76
     المعيارى
    0.66
     NSCoder
    0.64
     recevrez
    0.61
    Външни
    0.60
    rabaya
    0.59
    ագրություններ
    0.59
    ^(@)
    0.58
    RectangleBorder
    0.58
    nologue
    0.57
    Activations Density 0.013%

    No Known Activations