© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3097
    Prev
    Next
    INDEX
    Explanations

    the word 'military'

    oai_token-act-pair · gemini-2.0-flash
    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
     fought
    -0.84
     WAR
    -0.78
     battles
    -0.78
    ynb
    -0.77
     chiến
    -0.72
     ujednoznacz
    -0.71
     battle
    -0.71
    RemoveField
    -0.71
    WAR
    -0.70
    FIGHT
    -0.69
    POSITIVE LOGITS
     Military
    2.33
     military
    2.31
    Military
    2.27
    military
    2.27
     MILITARY
    2.17
     militaire
    1.63
     militares
    1.62
     Militär
    1.54
     militare
    1.48
     militari
    1.42
    Activations Density 0.005%

    No Known Activations