© 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. 4468
    Prev
    Next
    INDEX
    Explanations

    cancer

    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
    pidou
    -0.49
    olische
    -0.47
    n
    -0.45
     lượt
    -0.41
    bin
    -0.41
    IFS
    -0.41
    ську
    -0.40
    gaz
    -0.40
    k
    -0.39
    setVerticalGroup
    -0.39
    POSITIVE LOGITS
     estimés
    0.66
    CppMethod
    0.65
     calendriers
    0.65
     ProtoMessage
    0.63
     jadx
    0.63
    tanleria
    0.62
     跳转至
    0.62
    wnież
    0.61
     समीक्षक
    0.60
     kaynağından
    0.60
    Activations Density 0.001%

    No Known Activations