© 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. 0-CLT-HP
    7. 42602
    Prev
    Next
    INDEX
    Explanations

    war and battles

    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
     war
    -0.95
    ParallelGroup
    -0.58
     campaign
    -0.55
     Reducer
    -0.49
     job
    -0.48
     perang
    -0.48
     mind
    -0.47
     resultCode
    -0.46
     trail
    -0.45
     Cushion
    -0.45
    POSITIVE LOGITS
    houses
    0.72
     {}));
    0.71
    rooms
    0.68
    keepers
    0.68
    melons
    0.67
    boats
    0.66
    suits
    0.65
     referenties
    0.64
    adaptiveStyles
    0.64
    yards
    0.63
    Activations Density 0.009%

    No Known Activations