© 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. 4-CLT-HP
    7. 113
    Prev
    Next
    INDEX
    Explanations

    only

    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
    دانشنامهٔ
    -0.59
     ویکی‌پدیای
    -0.54
    UnusedPrivate
    -0.54
     mourut
    -0.51
     fuhr
    -0.50
    amo
    -0.50
     Waray
    -0.49
     consultato
    -0.49
    for
    -0.49
    am
    -0.49
    POSITIVE LOGITS
     take
    0.69
     jump
    0.66
     look
    0.65
     speculate
    0.65
     walk
    0.62
     see
    0.62
     move
    0.61
    kowej
    0.60
     think
    0.60
     keep
    0.59
    Activations Density 0.003%

    No Known Activations