© 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. 5-CLT-HP
    7. 5043
    Prev
    Next
    INDEX
    Explanations

    academic/scientific texts

    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
    :✨
    -0.57
    Hentet
    -0.54
    Mat
    -0.53
     ContentValues
    -0.53
     Cataloging
    -0.52
     Raptor
    -0.50
    hound
    -0.47
    Opt
    -0.46
     Har
    -0.46
    Doc
    -0.45
    POSITIVE LOGITS
     урна
    0.67
     aveug
    0.53
     ▸
    0.50
    CloseOperation
    0.50
    存于互联网档案馆
    0.50
    脚注の使い方
    0.49
     continúas
    0.49
     Paglinawan
    0.49
     eme
    0.48
    ագրություններ
    0.48
    Activations Density 0.001%

    No Known Activations