© 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. 5-CLT-HP
    7. 92529
    Prev
    Next
    INDEX
    Explanations

    open

    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
    Gweler
    -0.54
    RegressionTest
    -0.52
    enumi
    -0.47
    liothèque
    -0.46
    ker
    -0.45
    veri
    -0.45
    KER
    -0.43
    дъ
    -0.42
    TagMode
    -0.41
    <bos>
    -0.41
    POSITIVE LOGITS
     vendus
    0.72
    úrate
    0.65
     onCancelled
    0.64
    keyColumn
    0.63
    -------------</
    0.62
    principalColumn
    0.60
     defStyle
    0.60
     normaux
    0.60
    complexType
    0.57
    molly
    0.57
    Activations Density 0.002%

    No Known Activations