© 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. 73077
    Prev
    Next
    INDEX
    Explanations

    unusual words

    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
    KommentareTeilen
    -0.84
    principalTable
    -0.77
    MockMvc
    -0.72
    uxxxx
    -0.72
     Drapeau
    -0.71
     calendriers
    -0.68
     '\\;'
    -0.67
    awtextra
    -0.66
    AutoScale
    -0.64
    τά
    -0.64
    POSITIVE LOGITS
     gena
    0.46
    SneakyThrows
    0.46
     FetchType
    0.44
    дий
    0.41
    vian
    0.39
    انيا
    0.39
    endpush
    0.37
     audi
    0.37
     autorytatywna
    0.36
    AccessException
    0.36
    Activations Density 0.000%

    No Known Activations