© 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. 6681
    Prev
    Next
    INDEX
    Explanations

    references to metal coating or coating processes

    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
     picado
    -0.63
     surface
    -0.56
     Esp
    -0.54
    oldt
    -0.54
    ┘
    -0.54
    surface
    -0.52
    gefügt
    -0.52
    cio
    -0.51
     становника
    -0.51
    asmussen
    -0.50
    POSITIVE LOGITS
    coated
    2.75
     coated
    2.73
     coating
    2.70
     Coated
    2.64
    coating
    2.63
    coat
    2.61
     Coating
    2.59
     coat
    2.44
     Coat
    2.38
    Coat
    2.28
    Activations Density 0.007%

    No Known Activations