© 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. 1-CLT-HP
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    Militancy/Military conflicts

    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
    ########.
    -0.91
    Milit
    -0.81
     milit
    -0.73
    Personensuche
    -0.69
     Milit
    -0.68
     militant
    -0.67
    milit
    -0.63
    __(/*!
    -0.62
    fjspx
    -0.61
    ed
    -0.61
    POSITIVE LOGITS
    XMLSchema
    0.52
    KeySpec
    0.45
    ῖς
    0.45
     Odysseus
    0.45
     CBA
    0.44
    бливості
    0.43
    __':
    0.43
     Cze
    0.43
     Lorenz
    0.42
     gneiss
    0.42
    Activations Density 0.033%

    No Known Activations