© 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. 1-CLT-HP
    7. 14880
    Prev
    Next
    INDEX
    Explanations

    Technology and old west

    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
    verwijspagina
    -0.79
    المناصب
    -0.69
    Jeografia
    -0.68
     unknownFields
    -0.66
     disambiguazione
    -0.65
    complexContent
    -0.65
    httphttps
    -0.64
    ⓧ
    -0.62
     resourceCulture
    -0.62
    :✨
    -0.59
    POSITIVE LOGITS
    enzuela
    0.54
    s
    0.54
    aleb
    0.52
    onPressed
    0.52
    lüğ
    0.49
    nucle
    0.49
    DataBind
    0.49
    TableAdapter
    0.49
    Cerrar
    0.49
    ség
    0.47
    Activations Density 0.032%

    No Known Activations