© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    references to chemical additives and substances used in formulations and materials

    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
     Meksiku
    -0.58
     gills
    -0.58
    yntaxException
    -0.56
     entendu
    -0.54
     fresher
    -0.54
    WithIOException
    -0.53
     terraces
    -0.52
     समीक्षक
    -0.51
     Meny
    -0.50
    metra
    -0.50
    POSITIVE LOGITS
    /*
    0.62
    گزاری
    0.62
    domada
    0.61
    /**
    0.60
    ագրություններ
    0.60
     StatelessWidget
    0.57
    Ārējās
    0.57
    ticides
    0.55
     AssemblyTitle
    0.55
    ::_('
    0.55
    Activations Density 0.675%

    No Known Activations