© 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. 0-CLT-HP
    7. 94186
    Prev
    Next
    INDEX
    Explanations

    gender

    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
     female
    -1.66
     male
    -1.66
    male
    -1.66
     Female
    -1.66
    female
    -1.61
     Male
    -1.55
    Female
    -1.53
    Male
    -1.51
     MALE
    -1.36
     FEMALE
    -1.34
    POSITIVE LOGITS
    CppMethod
    0.63
    atouille
    0.61
    \{\\
    0.58
     defStyle
    0.57
    JTable
    0.57
    ReusableCell
    0.56
     nahilalakip
    0.56
    Boas
    0.55
    Portály
    0.54
    providedIn
    0.52
    Activations Density 1.456%

    No Known Activations