© 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. 4126
    Prev
    Next
    INDEX
    Explanations

    references to a type of manufacturing or processing facility, specifically a mill

    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
    IntoConstraints
    -0.85
     Corcoran
    -0.68
     Lorca
    -0.66
     caverns
    -0.65
     ivelany
    -0.64
     Caine
    -0.64
    CJK
    -0.63
    φή
    -0.62
    quakes
    -0.61
     lycra
    -0.61
    POSITIVE LOGITS
     mill
    3.25
     Mill
    3.13
    Mill
    2.95
    mill
    2.80
     MILL
    2.80
    MILL
    2.69
     mills
    2.56
     Mills
    2.27
     MILLS
    2.14
     mil
    2.09
    Activations Density 0.041%

    No Known Activations