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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91194
    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
    -0.95
    war
    -0.91
    War
    -0.89
     war
    -0.88
    WAR
    -0.81
     WAR
    -0.71
     guerra
    -0.66
     guerre
    -0.65
    wars
    -0.55
    战争
    -0.51
    POSITIVE LOGITS
     itſelf
    1.22
     myſelf
    1.13
     pleaſure
    1.11
     Theſe
    1.10
     doubtnut
    1.08
     themſelves
    1.05
    ſelf
    1.03
     poffible
    1.02
    AndEndTag
    0.98
    ſelves
    0.96
    Activations Density 1.551%

    No Known Activations