© 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. 0-CLT-HP
    7. 41511
    Prev
    Next
    INDEX
    Explanations

    Grace

    np_max-act · 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
    lium
    -0.60
    oui
    -0.52
    ial
    -0.50
    edom
    -0.48
    gely
    -0.47
    ziger
    -0.47
    ately
    -0.47
     Yates
    -0.45
    ead
    -0.45
    ם
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    ⓧ
    0.82
     crdi
    0.81
     doubtnut
    0.79
    ViewFeatures
    0.78
     Monfieur
    0.77
     Mahomet
    0.74
    IUrlHelper
    0.74
    Autoritní
    0.73
     Lancet
    0.73
    Activations Density 0.092%

    No Known Activations