© 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. 0-CLT-HP
    7. 43484
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
     Bioaccumulative
    -0.55
    ఔ
    -0.55
     Вікі
    -0.53
    новниш
    -0.52
     BaseModel
    -0.49
    akir
    -0.47
     négo
    -0.47
     uč
    -0.46
     marcadas
    -0.46
    ثيق
    -0.45
    POSITIVE LOGITS
     ***!
    0.82
    ⓧ
    0.77
    +#+#
    0.68
     Roskov
    0.68
    Rüyada
    0.66
    protoc
    0.62
    //
    0.61
    AddHtmlAttribute
    0.61
     autorytatywna
    0.61
     unknownFields
    0.60
    Activations Density 0.137%

    No Known Activations