© 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. 71962
    Prev
    Next
    INDEX
    Explanations

    Starts with "Tri"

    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
    MigrationBuilder
    -0.50
    AddTagHelper
    -0.49
     comarca
    -0.47
     gyrus
    -0.46
    HasForeignKey
    -0.46
    évaluateur
    -0.46
    parsedMessage
    -0.46
    umahan
    -0.45
    aryti
    -0.45
    EndGlobalSection
    -0.45
    POSITIVE LOGITS
     forbindelse
    0.53
    ffon
    0.52
     réseaux
    0.52
     campuran
    0.50
     Normdatei
    0.50
    conio
    0.49
    interopRequire
    0.48
    pezif
    0.47
    vaal
    0.47
     NSCoder
    0.46
    Activations Density 0.001%

    No Known Activations