© 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. 20-CLT-HP
    7. 77595
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · 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
     Woman
    -1.02
     Women
    -0.99
     Boys
    -0.97
    Woman
    -0.96
    Boys
    -0.95
    Women
    -0.94
     Womens
    -0.89
    WOMEN
    -0.88
     woman
    -0.87
     boys
    -0.87
    POSITIVE LOGITS
    InputTagHelper
    0.46
    zun
    0.41
     Sus
    0.40
     Axel
    0.40
    AntiForgeryToken
    0.39
    lulu
    0.39
     OBL
    0.39
    SharedDtor
    0.39
     g
    0.38
    Cyfeiriadau
    0.38
    Activations Density 0.003%

    No Known Activations