© 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. 5-CLT-HP
    7. 97934
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Theſe
    -0.79
     itſelf
    -0.79
     Jefus
    -0.78
    Искәрмәләр
    -0.76
    Jeografia
    -0.72
     Eſ
    -0.72
    Билгалдахарш
    -0.72
    seamnă
    -0.70
     Efq
    -0.70
     uſed
    -0.69
    POSITIVE LOGITS
     father
    0.56
    :@"
    0.55
     founder
    0.54
     grandfather
    0.52
     “
    0.52
    lifier
    0.50
     inventor
    0.50
     creator
    0.49
     Godfather
    0.48
     mother
    0.48
    Activations Density 0.003%

    No Known Activations