© 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. 5-CLT-HP
    7. 3331
    Prev
    Next
    INDEX
    Explanations

    military

    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
     />\
    -0.56
    agine
    -0.46
    estyle
    -0.42
    psons
    -0.42
    setContentView
    -0.41
    蒻
    -0.41
    cuits
    -0.41
    gany
    -0.40
    riche
    -0.40
    ;}
    -0.40
    POSITIVE LOGITS
     Military
    0.86
    Military
    0.83
    military
    0.79
     MILITARY
    0.79
    Army
    0.79
     militaire
    0.77
     military
    0.77
    army
    0.75
     Militar
    0.73
     army
    0.72
    Activations Density 0.003%

    No Known Activations