© 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. 92188
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Rujukan
    -0.48
    </strong>
    -0.46
     <!--
    -0.45
    oneg
    -0.45
    roek
    -0.43
     Purposes
    -0.43
    uel
    -0.42
    yl
    -0.41
     “
    -0.40
     "
    -0.40
    POSITIVE LOGITS
    contentLoaded
    0.75
    enderror
    0.71
     Савезне
    0.68
    webElementXpaths
    0.68
     Efq
    0.67
    تقاوى
    0.66
     Chwiliwch
    0.65
    ."));
    0.65
    MigrationBuilder
    0.63
    الإنجليزية
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.