© 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. 72678
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
    ChildScrollView
    -0.63
     nahilalakip
    -0.63
    mybatisplus
    -0.61
    AndEndTag
    -0.59
    windowFixed
    -0.56
    DoubleQuotes
    -0.56
     Cæsar
    -0.55
     Monfieur
    -0.53
    cionario
    -0.52
    CodeAttribute
    -0.52
    POSITIVE LOGITS
    lccn
    0.57
    ècie
    0.52
    elemField
    0.52
    لينكات
    0.51
    addCriterion
    0.50
    entran
    0.50
     bank
    0.50
     onBind
    0.49
     Heath
    0.48
    var
    0.47
    Activations Density 0.000%

    No Known Activations