© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    Event listings and formal language

    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
    rungsseite
    -0.73
    ThroughAttribute
    -0.65
    CloseOperation
    -0.60
    TemporalType
    -0.58
    ьаж
    -0.55
    parsedMessage
    -0.55
    WebControls
    -0.53
     Wiktionnaire
    -0.53
     MessageBoxIcon
    -0.53
    ellemző
    -0.52
    POSITIVE LOGITS
    出版年
    0.67
    verifyException
    0.57
    tanleria
    0.54
     ModelExpression
    0.52
     leading
    0.52
     насељу
    0.52
    </tfoot>
    0.51
    varargin
    0.48
    Spoljašnje
    0.47
    zeß
    0.46
    Activations Density 0.003%

    No Known Activations