© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12646
    Prev
    Next
    INDEX
    Explanations

    references to specific pharmaceutical compounds, formulations, and related medical or chemical terms

    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
     geha
    -0.66
    Skocz
    -0.63
    tribune
    -0.61
     inéd
    -0.60
     Sciento
    -0.57
     Monfieur
    -0.56
    ientôt
    -0.56
    当初
    -0.56
    Filmografie
    -0.56
    fromCharCode
    -0.56
    POSITIVE LOGITS
    xaml
    0.80
    Either
    0.71
    DoubleQuotes
    0.66
    Regardless
    0.65
     Regardless
    0.64
    nteral
    0.63
     Emma
    0.62
    ().__
    0.61
     Either
    0.61
    brata
    0.59
    Activations Density 0.094%

    No Known Activations