© 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. 93483
    Prev
    Next
    INDEX
    Explanations

    code and software

    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
     kasarigan
    -0.71
    principalColumn
    -0.55
     giustizia
    -0.55
     genoux
    -0.54
     prisonniers
    -0.54
    Referanser
    -0.52
     enfans
    -0.52
     malheure
    -0.51
     avoient
    -0.50
    참고
    -0.49
    POSITIVE LOGITS
    styleType
    0.63
    SCHE
    0.54
    YMS
    0.54
     support
    0.53
    sche
    0.52
    OGND
    0.52
     conversion
    0.52
     rowspan
    0.51
     schme
    0.51
    kim
    0.51
    Activations Density 0.001%

    No Known Activations