© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92942
    Prev
    Next
    INDEX
    Explanations

    Historical figures and places

    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
     king
    -1.93
     King
    -1.76
    King
    -1.76
     KING
    -1.63
    king
    -1.52
    KING
    -1.32
     kings
    -0.97
     rey
    -0.95
     король
    -0.90
     kingdom
    -0.87
    POSITIVE LOGITS
     ujednoznacz
    0.68
    zzleHttp
    0.62
    lgari
    0.60
    ctibles
    0.59
    lably
    0.57
     mépris
    0.55
    ismet
    0.54
    gwin
    0.54
    onym
    0.53
     Unies
    0.53
    Activations Density 0.063%

    No Known Activations