© 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. 0-CLT-HP
    7. 93912
    Prev
    Next
    INDEX
    Explanations

    word, recent

    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
    Word
    -0.88
     Word
    -0.71
    word
    -0.65
    sses
    -0.53
    ing
    -0.51
    ed
    -0.50
     word
    -0.47
    mal
    -0.47
    GeoNames
    -0.46
    Recent
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.83
     itſelf
    0.76
    leſs
    0.75
    .";
    0.75
     Efq
    0.74
     $_"
    0.73
    berdayakan
    0.72
     Forumite
    0.72
    Jeografia
    0.72
    )";
    0.71
    Activations Density 0.161%

    No Known Activations