© 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. 1-CLT-HP
    7. 15827
    Prev
    Next
    INDEX
    Explanations

    ilitary

    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
     militia
    -0.56
    RegistryLite
    -0.54
    ding
    -0.50
    tlement
    -0.49
    mybatisplus
    -0.49
     joaat
    -0.48
    mption
    -0.46
    SystemColors
    -0.46
    sho
    -0.45
    ilitary
    -0.45
    POSITIVE LOGITS
     ExecuteAsync
    0.63
    Datuak
    0.63
     framed
    0.60
    invokeLater
    0.57
    aA
    0.56
    Morfologia
    0.56
     orgánica
    0.55
    Enllaces
    0.54
    DrawerToggle
    0.54
    رشف
    0.54
    Activations Density 0.019%

    No Known Activations