© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90579
    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
    -2.45
     War
    -2.36
    War
    -2.13
    war
    -1.83
     WAR
    -1.83
     guerra
    -1.44
    WAR
    -1.40
     guerre
    -1.37
     krig
    -1.04
    戦争
    -1.02
    POSITIVE LOGITS
     itſelf
    0.95
    ſelf
    0.77
     myſelf
    0.71
     Jefus
    0.71
    postolic
    0.67
     Мексичка
    0.67
    Життєпис
    0.67
     Majefty
    0.67
    providedIn
    0.66
    GEBURTS
    0.66
    Activations Density 0.079%

    No Known Activations