© 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. 4-CLT-HP
    7. 908
    Prev
    Next
    INDEX
    Explanations

    race and ethnicity

    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
     StatefulWidget
    -0.61
     незавершена
    -0.58
     murale
    -0.57
     törvény
    -0.56
     alluminio
    -0.56
     circulaire
    -0.55
    MemoryWarning
    -0.54
     mergeFrom
    -0.53
    AutoScale
    -0.53
    racle
    -0.50
    POSITIVE LOGITS
    userdetails
    0.55
    찮
    0.53
    ubit
    0.51
    SenderId
    0.51
    tiss
    0.48
     Lor
    0.47
    olus
    0.47
    indices
    0.46
    Бахар
    0.46
    odils
    0.46
    Activations Density 0.003%

    No Known Activations