© 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. 0-RES-MATRYOSHKA-DC
    7. 11765
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of industrial machinery or 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
     bats
    -0.83
     inning
    -0.77
     batsman
    -0.75
     innings
    -0.67
     fielder
    -0.67
     OnInit
    -0.66
     batted
    -0.66
     pitcher
    -0.65
     knuckle
    -0.64
    GeneratedCode
    -0.61
    POSITIVE LOGITS
     Bat
    2.14
    Bat
    1.69
     BoxFit
    0.74
     оригіналу
    0.62
     BATT
    0.55
    atguigu
    0.55
    setVerticalGroup
    0.52
    findpost
    0.52
    richTextPanel
    0.52
     Batavia
    0.52
    Activations Density 0.002%

    No Known Activations