© 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. 20-CLT-HP
    7. 72902
    Prev
    Next
    INDEX
    Explanations

    coding

    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
    帖最后由
    -0.82
     autorytatywna
    -0.78
     ostavi
    -0.75
     noqa
    -0.71
     noDo
    -0.67
     Ανακτήθηκε
    -0.66
    MigrationBuilder
    -0.64
    новништво
    -0.63
    ContentAsync
    -0.61
     оригіналу
    -0.60
    POSITIVE LOGITS
     HasFactory
    0.60
    (!__
    0.50
    (&$
    0.40
    uParam
    0.39
    )$-
    0.38
    *$
    0.37
    CompleteListener
    0.36
    glBindBuffer
    0.35
    Aph
    0.35
     unlock
    0.35
    Activations Density 0.002%

    No Known Activations