© 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. 2-RES-MATRYOSHKA-DC
    7. 4081
    Prev
    Next
    INDEX
    Explanations

    mentions of military units involved in specific battles or troop movements

    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
    parsedMessage
    -0.82
    expandindo
    -0.68
    esModule
    -0.68
    PreferredItem
    -0.63
    gestone
    -0.63
    adaptiveStyles
    -0.61
     nahilalakip
    -0.60
     MenuView
    -0.60
    ionario
    -0.58
    BufferException
    -0.58
    POSITIVE LOGITS
     crew
    1.27
     squad
    1.16
    crew
    1.05
     gang
    0.98
     team
    0.98
     crews
    0.96
     workforce
    0.92
     brigade
    0.91
     Squad
    0.91
     staff
    0.89
    Activations Density 0.683%

    No Known Activations