© 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. 4-CLT-HP
    7. 1937
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
    KommentareTeilen
    -0.61
    .”)
    -0.60
    Personensuche
    -0.56
    ),”
    -0.56
     resourceCulture
    -0.53
     bereavement
    -0.50
    stood
    -0.50
    gone
    -0.50
    OPIN
    -0.49
    rrggbb
    -0.49
    POSITIVE LOGITS
    IsContent
    0.67
    ValueStyle
    0.57
     Deum
    0.56
    complexType
    0.54
    titleMargin
    0.54
    lismo
    0.53
     مواليد
    0.53
    multer
    0.50
     can
    0.50
     initComponents
    0.50
    Activations Density 0.004%

    No Known Activations