© 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. 7061
    Prev
    Next
    INDEX
    Explanations

    references to military units, specifically U.S. Air Force squadrons and related military organizational terms

    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
    Попис
    -0.99
    featureID
    -0.86
     protoimpl
    -0.85
     NSCoder
    -0.85
    WebVitals
    -0.82
     виправивши
    -0.80
    memoized
    -0.78
    EDEFAULT
    -0.78
    expandindo
    -0.75
    intios
    -0.72
    POSITIVE LOGITS
    ↵
    0.56
    chule
    0.42
     каза
    0.41
     ||
    0.39
    ingeki
    0.38
    eltzer
    0.38
     vezes
    0.37
    matig
    0.37
    ObjectModel
    0.37
     veces
    0.36
    Activations Density 1.758%

    No Known Activations