© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44075
    Prev
    Next
    INDEX
    Explanations

    parental

    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
    Билгалдахарш
    -0.76
    +#+#
    -0.69
    ValueStyle
    -0.68
     autorytatywna
    -0.66
    MigrationBuilder
    -0.66
     kaarangay
    -0.64
    يكب
    -0.63
    e
    -0.63
     חיצוניים
    -0.62
    Geplaatst
    -0.62
    POSITIVE LOGITS
    ers
    0.60
     Braga
    0.57
     Viana
    0.56
     Theſe
    0.56
     ſta
    0.54
     Monfieur
    0.54
    ida
    0.52
     Murch
    0.52
     damska
    0.50
    ridos
    0.50
    Activations Density 0.691%

    No Known Activations