© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75721
    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
    licans
    -0.42
     juges
    -0.42
    isers
    -0.40
     maîtres
    -0.40
     pères
    -0.38
    Skocz
    -0.36
     collègues
    -0.36
     conseillers
    -0.35
     Bees
    -0.35
    '
    -0.34
    POSITIVE LOGITS
    UrlResolution
    0.71
    RenderAtEndOf
    0.69
    SharedDtor
    0.68
     informée
    0.66
     ComVisible
    0.65
    مصادر
    0.65
    RectangleBorder
    0.65
     Shakspeare
    0.64
    richTextPanel
    0.63
     Hift
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.