© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71629
    Prev
    Next
    INDEX
    Explanations

    -

    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
     createSlice
    -0.61
     виправивши
    -0.58
     &___
    -0.56
    enumi
    -0.54
     noDo
    -0.52
    AddHtmlAttribute
    -0.51
    RegressionTest
    -0.48
     Signalez
    -0.48
    enumii
    -0.46
    Népesség
    -0.45
    POSITIVE LOGITS
     MCI
    0.56
    出版年
    0.53
    jarse
    0.52
    MCI
    0.50
    cetes
    0.50
    ardan
    0.48
    клопе
    0.48
    üm
    0.48
     {:.
    0.48
     CARD
    0.48
    Activations Density 0.000%

    No Known Activations