© 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. 0-CLT-HP
    7. 41492
    Prev
    Next
    INDEX
    Explanations

    technical documents excerpts

    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
     Billi
    -0.94
    Billi
    -0.82
    :✨
    -0.73
    Хьажоргаш
    -0.67
    billi
    -0.65
    Cyfeiriadau
    -0.64
    ilat
    -0.64
    RectangleBorder
    -0.63
     iprot
    -0.61
    Jeografia
    -0.60
    POSITIVE LOGITS
    Geplaatst
    0.57
    gde
    0.52
    insics
    0.51
    signable
    0.50
    pageTitle
    0.49
    ARGB
    0.47
    warten
    0.46
    olata
    0.46
    [](
    0.46
    شهاد
    0.45
    Activations Density 0.809%

    No Known Activations