© 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. 77981
    Prev
    Next
    INDEX
    Explanations

    continue

    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
     autorytatywna
    -0.56
     оригіналу
    -0.53
    />";
    -0.52
     Allo
    -0.52
    BeginContext
    -0.51
    новништво
    -0.51
     AttributeSet
    -0.50
     TAMBIÉN
    -0.50
     typelib
    -0.49
     continuation
    -0.49
    POSITIVE LOGITS
    a
    0.58
     unab
    0.56
     a
    0.56
     generazione
    0.54
     und
    0.54
     aveug
    0.52
     kuchni
    0.51
     vrijwilli
    0.51
    Obituary
    0.51
     A
    0.51
    Activations Density 0.001%

    No Known Activations