© 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. 20-CLT-HP
    7. 73591
    Prev
    Next
    INDEX
    Explanations

    Code snippets/foreign languages

    np_max-act-logits · 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
     Савезне
    -0.69
     catching
    -0.67
    impianto
    -0.63
    urlpatterns
    -0.61
     pylint
    -0.60
    loyer
    -0.59
     때문
    -0.58
     filling
    -0.58
     Carn
    -0.58
    WSGI
    -0.57
    POSITIVE LOGITS
     مرئيه
    0.47
     kasarigan
    0.46
     dec
    0.44
     समीक्षाओं
    0.41
    さんは
    0.41
    NOPQRST
    0.41
     pinulongan
    0.40
     esper
    0.40
     made
    0.39
    rook
    0.38
    Activations Density 0.012%

    No Known Activations