© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5332
    Prev
    Next
    INDEX
    Explanations

    references to military branches and personnel

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     war
    -0.88
     WAR
    -0.85
     War
    -0.82
    War
    -0.81
    war
    -0.79
     Volcan
    -0.70
     fight
    -0.69
    WAR
    -0.67
    FIGHT
    -0.66
     FIGHT
    -0.65
    POSITIVE LOGITS
     Army
    3.20
    Army
    2.98
     army
    2.73
    army
    2.59
     ARMY
    2.53
     armies
    1.81
     ejército
    1.74
     Armee
    1.73
    armée
    1.72
     Armies
    1.67
    Activations Density 0.024%

    No Known Activations