© 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. 15555
    Prev
    Next
    INDEX
    Explanations

    Rockets and cells

    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
     kasarigan
    -0.83
    rungsseite
    -0.64
    Geplaatst
    -0.63
     arşivlendi
    -0.61
    bentar
    -0.57
     ProtoMessage
    -0.57
     étoit
    -0.56
    hésite
    -0.56
    zner
    -0.55
    Hentet
    -0.54
    POSITIVE LOGITS
    ISupport
    0.74
    adays
    0.56
    webgl
    0.51
    Naissance
    0.50
    出版年
    0.49
    QtGui
    0.47
    writeField
    0.47
    *************/
    0.47
    expandindo
    0.46
     Coen
    0.45
    Activations Density 0.027%

    No Known Activations