© 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. 20-CLT-HP
    7. 73490
    Prev
    Next
    INDEX
    Explanations

    Code, documents, unusual terms

    np_max-act-logits · 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
    AddTagHelper
    -0.67
     <=",
    -0.63
    awtextra
    -0.59
     onlyOwner
    -0.54
     isComment
    -0.52
    bigoplus
    -0.52
    kloped
    -0.51
    :✨
    -0.51
     مشين
    -0.50
     RCA
    -0.50
    POSITIVE LOGITS
    findpost
    0.60
    Par
    0.54
    Suffix
    0.50
     acid
    0.48
    لق
    0.48
    protoimpl
    0.46
     समीक्षाएं
    0.46
    はじめに
    0.46
     InputDecoration
    0.46
     Acid
    0.46
    Activations Density 0.000%

    No Known Activations