© 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. 4466
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    moveToFirst
    -0.69
     useSelector
    -0.59
     pstmt
    -0.59
     avoient
    -0.59
     rospy
    -0.59
     HasFactory
    -0.58
    ColumnHeaders
    -0.58
    %")
    -0.57
    makeConstraints
    -0.56
    UnsafeEnabled
    -0.56
    POSITIVE LOGITS
     WEAR
    0.50
     Boe
    0.50
     باست
    0.48
    WEAR
    0.47
    anthin
    0.47
     Pome
    0.46
    apor
    0.46
    ్రామ
    0.46
    uc
    0.46
     Wear
    0.45
    Activations Density 0.012%

    No Known Activations