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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13860
    Prev
    Next
    INDEX
    Explanations

    references to protective body armor or armor-like equipment

    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
    BASEPATH
    -0.66
    ViewImports
    -0.58
    الحياه
    -0.57
    érables
    -0.55
     Veter
    -0.54
     leg
    -0.52
    ranean
    -0.52
     kiệm
    -0.51
     glyphicon
    -0.51
    WebServlet
    -0.49
    POSITIVE LOGITS
     armor
    3.33
     armour
    3.06
     Armor
    2.94
    Armor
    2.61
    armor
    2.58
     Armour
    2.22
     armored
    1.66
     armadura
    1.54
     armoured
    1.51
     Armored
    1.35
    Activations Density 0.001%

    No Known Activations