© 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. 0-CLT-HP
    7. 41732
    Prev
    Next
    INDEX
    Explanations

    ont

    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
    ont
    -1.58
    ONT
    -1.23
    nt
    -1.09
    NT
    -0.95
     ont
    -0.83
    ontin
    -0.77
    ontes
    -0.75
     nt
    -0.75
    ontan
    -0.73
    MethodManager
    -0.71
    POSITIVE LOGITS
    SharedCtor
    0.67
    ttino
    0.62
    __(/*!
    0.56
    s
    0.55
    sid
    0.52
    yarnpkg
    0.52
     kasarigan
    0.50
    CMY
    0.48
    rungsseite
    0.47
    ds
    0.47
    Activations Density 1.729%

    No Known Activations