Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73885
    Prev
    Next
    INDEX
    Explanations

    lingual

    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
     zove
    -0.35
    SharedDtor
    -0.31
     ostavi
    -0.30
    日前
    -0.30
     resultCode
    -0.29
    oluble
    -0.29
     informée
    -0.29
    PROLOG
    -0.29
    addRow
    -0.28
     bebes
    -0.28
    POSITIVE LOGITS
     myſelf
    0.84
     Jefus
    0.83
     Theſe
    0.82
     Majefty
    0.79
     themſelves
    0.77
     Meck
    0.77
     Houſe
    0.76
     Reſ
    0.76
     itſelf
    0.73
     ―――――
    0.73
    Activations Density 0.000%

    No Known Activations