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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4886
    Prev
    Next
    INDEX
    Explanations

    import

    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
     Мексичка
    -1.05
     Efq
    -1.02
     Monfieur
    -0.95
    Geplaatst
    -0.93
     myſelf
    -0.93
    ValueStyle
    -0.92
     purpoſe
    -0.91
    RegistryLite
    -0.91
    MigrationBuilder
    -0.89
     ModelExpression
    -0.80
    POSITIVE LOGITS
    ".
    0.49
    .
    0.47
     from
    0.46
    .</
    0.45
    ).
    0.45
     due
    0.45
    ход
    0.45
    ."
    0.45
    ”.
    0.44
     in
    0.43
    Activations Density 0.007%

    No Known Activations