© 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. 15590
    Prev
    Next
    INDEX
    Explanations

    san

    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
    san
    -1.35
     san
    -1.23
    San
    -1.20
     San
    -1.16
     sanction
    -0.93
     Sandi
    -0.88
     Sanford
    -0.84
     SAN
    -0.84
    SAN
    -0.83
     sanitize
    -0.83
    POSITIVE LOGITS
    GEBURTSDATUM
    0.48
    etti
    0.41
    rard
    0.41
     Unavailable
    0.40
    ább
    0.40
    DNF
    0.39
    <bos>
    0.39
    Brak
    0.38
    Nab
    0.37
    toolStripButton
    0.37
    Activations Density 0.018%

    No Known Activations