© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15698
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    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
    IE
    -0.66
    a
    -0.46
    aurus
    -0.44
    rieg
    -0.43
     IE
    -0.43
    ه
    -0.42
    e
    -0.41
    er
    -0.41
     secund
    -0.41
    yip
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.77
     onlyOwner
    0.76
    出版年
    0.76
     protoimpl
    0.70
    ContentAsync
    0.70
    HtmlAttribute
    0.69
    TemporalType
    0.69
    LookAnd
    0.69
    XMLSchema
    0.65
    NewUrlParser
    0.65
    Activations Density 0.020%

    No Known Activations