© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95468
    Prev
    Next
    INDEX
    Explanations

    M

    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
    mặt
    -0.59
    SBATCH
    -0.59
    UALLY
    -0.54
    $}}
    -0.54
    endaft
    -0.53
     allez
    -0.50
    bbene
    -0.50
    vieux
    -0.50
    følge
    -0.50
     exécu
    -0.50
    POSITIVE LOGITS
     resourceCulture
    0.77
    +#+#
    0.77
     GenerationType
    0.73
    <bos>
    0.67
    $_['
    0.65
    InstrumentedTest
    0.59
    DockStyle
    0.59
    ViewFeatures
    0.56
    <>("
    0.55
    ViewImports
    0.54
    Activations Density 0.214%

    No Known Activations