© 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. 4-CLT-HP
    7. 657
    Prev
    Next
    INDEX
    Explanations

    military/war

    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
    +#+
    -0.47
     Anomaly
    -0.43
    LError
    -0.43
     hereof
    -0.42
     Colt
    -0.42
     benefited
    -0.41
    রণ
    -0.41
     dawg
    -0.40
     judicial
    -0.40
     Guter
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.69
     ligiloj
    0.61
     Exactos
    0.58
     esternos
    0.56
    migrationBuilder
    0.56
     yyl
    0.55
    MemoryWarning
    0.54
     referenties
    0.54
    stätten
    0.54
    complexContent
    0.53
    Activations Density 0.003%

    No Known Activations