© 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. 14968
    Prev
    Next
    INDEX
    Explanations

    all

    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
    Bronnen
    -0.55
    orianCalendar
    -0.55
    kyard
    -0.53
    rektur
    -0.53
    aroos
    -0.51
    jemy
    -0.49
    zzazione
    -0.49
     trover
    -0.49
     appui
    -0.49
    forChild
    -0.47
    POSITIVE LOGITS
     utafitiHapana
    0.68
     Paglinawan
    0.65
    الإنجليزية
    0.58
    Архівовано
    0.58
     cherchés
    0.57
    ::_('
    0.57
    KURZBESCHREIBUNG
    0.54
     незавершена
    0.53
    Према
    0.52
    Enllaços
    0.52
    Activations Density 0.015%

    No Known Activations