© 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. 73119
    Prev
    Next
    INDEX
    Explanations

    code/scientific papers

    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
    uta
    -0.59
    zerland
    -0.53
    AddTagHelper
    -0.52
    uzen
    -0.52
     ambientales
    -0.48
     solares
    -0.47
     imprimée
    -0.46
     placée
    -0.46
     跳转至
    -0.46
     flesta
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.81
    migrationBuilder
    0.78
    tagHelperRunner
    0.68
     AssemblyTitle
    0.64
    AccessorTable
    0.60
    libft
    0.58
    featureID
    0.56
    ंदीखरीदारी
    0.56
    ISupport
    0.55
     getItemId
    0.54
    Activations Density 0.003%

    No Known Activations