© 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. 9091
    Prev
    Next
    INDEX
    Explanations

    gender and sex

    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
    Personensuche
    -1.00
    IntoConstraints
    -0.72
    Geplaatst
    -0.69
    hysema
    -0.69
     تضيفلها
    -0.69
     alluminio
    -0.67
    лтемелер
    -0.67
    ascin
    -0.66
    tableFuture
    -0.66
    knię
    -0.65
    POSITIVE LOGITS
    
    0.49
     MediatR
    0.44
     Orrell
    0.40
    fda
    0.39
     Verenig
    0.39
     licensee
    0.38
     propOrder
    0.38
    IsPostBack
    0.37
    ::::::::
    0.37
    BeginInit
    0.37
    Activations Density 0.017%

    No Known Activations