© 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. 10417
    Prev
    Next
    INDEX
    Explanations

    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
    war
    -0.77
     War
    -0.76
    War
    -0.72
     war
    -0.69
     WAR
    -0.60
    waran
    -0.57
    WAR
    -0.56
     nakalista
    -0.49
     inoxydable
    -0.49
     quæ
    -0.48
    POSITIVE LOGITS
    ngdoc
    0.84
    __((
    0.67
     intptr
    0.67
    MessageOf
    0.65
    complexContent
    0.62
    endpush
    0.60
     snippetHide
    0.59
     GenerationType
    0.57
     propOrder
    0.57
    Datuak
    0.57
    Activations Density 0.030%

    No Known Activations