© 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. 9304
    Prev
    Next
    INDEX
    Explanations

    men

    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
    BeginContext
    -0.76
    最快更新
    -0.67
    ագրություններ
    -0.67
     Wallflower
    -0.66
    PyErr
    -0.65
    enumii
    -0.63
    thalle
    -0.62
    tubers
    -0.62
    RenderAtEndOf
    -0.61
    ViewFeatures
    -0.61
    POSITIVE LOGITS
     femininas
    0.50
    UVWXYZ
    0.47
     sprend
    0.45
    LM
    0.44
     ouvertes
    0.43
     çay
    0.42
     femininos
    0.41
     colorés
    0.41
     aisladas
    0.40
     élevées
    0.40
    Activations Density 0.084%

    No Known Activations