© 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. 5938
    Prev
    Next
    INDEX
    Explanations

    this

    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
     disponibilités
    -0.49
    there
    -0.48
     simplifié
    -0.46
     robbed
    -0.45
    DockStyle
    -0.45
    ่านั้น
    -0.44
    been
    -0.44
    stood
    -0.44
    THERE
    -0.44
    There
    -0.43
    POSITIVE LOGITS
    Rüyada
    0.71
    DeleteBehavior
    0.67
    principalTable
    0.66
     vectorielles
    0.58
     estekak
    0.58
     BrowserRouter
    0.57
     समीक्षाओं
    0.55
    saraba
    0.55
     Vainqueur
    0.54
    :✨
    0.54
    Activations Density 0.015%

    No Known Activations