© 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. 20-CLT-HP
    7. 76395
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, and functions

    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
    GEBURTSDATUM
    -0.75
    quelize
    -0.64
    WithIOException
    -0.63
    tagHelperRunner
    -0.61
    WebVitals
    -0.59
    urlpatterns
    -0.56
    下载附件
    -0.55
    èdia
    -0.54
    TagMode
    -0.54
     "..\..\
    -0.54
    POSITIVE LOGITS
    Mf
    0.51
    gigi
    0.50
    enumi
    0.49
    endpush
    0.49
    json
    0.48
     démocr
    0.48
    americanos
    0.47
     définiti
    0.46
     gts
    0.46
    forKey
    0.45
    Activations Density 0.003%

    No Known Activations