© 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. 72655
    Prev
    Next
    INDEX
    Explanations

    St

    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
    uxxxx
    -0.74
    queryInterface
    -0.71
    HomeAsUpEnabled
    -0.64
    parsedMessage
    -0.61
    <bos>
    -0.61
    findpost
    -0.56
    ())));
    -0.56
    ellemző
    -0.55
    )$}
    -0.54
    ACJA
    -0.54
    POSITIVE LOGITS
    ">//
    0.61
     lenker
    0.55
    ggere
    0.47
    waitKey
    0.46
     commerciaux
    0.44
    contentLoaded
    0.43
     chré
    0.43
     الميل
    0.42
    قایناقلار
    0.41
     cerrados
    0.41
    Activations Density 0.002%

    No Known Activations