© 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. 903
    Prev
    Next
    INDEX
    Explanations

    Pronouns referring to people

    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
    gameserver
    -0.65
     resourceCulture
    -0.65
    NewUrlParser
    -0.58
    XmlAccessType
    -0.53
    Bodies
    -0.52
    
    -0.52
    ője
    -0.52
    uarkan
    -0.50
     JADX
    -0.50
     Familienname
    -0.50
    POSITIVE LOGITS
    uação
    0.58
    bergh
    0.52
    Tikang
    0.50
    BoxShadow
    0.48
    ukau
    0.47
    Zobacz
    0.47
    didSet
    0.47
    ￡
    0.47
    maic
    0.45
     تضيفلها
    0.45
    Activations Density 0.003%

    No Known Activations