© 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. 11499
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound, namely "cholesterol."

    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
     mergeFrom
    -0.71
    addContainerGap
    -0.54
     findes
    -0.52
    DataPropertyName
    -0.51
    ENTAL
    -0.50
     rental
    -0.48
    Thom
    -0.48
    REAT
    -0.48
    (!__
    -0.48
    ésor
    -0.48
    POSITIVE LOGITS
    ;->
    0.92
    GraphicsUnit
    0.72
    Stayed
    0.65
     piss
    0.65
     Cray
    0.65
     ISBN
    0.65
    ConverterFactory
    0.65
    esomeness
    0.63
    ISBN
    0.62
    hysema
    0.62
    Activations Density 0.149%

    No Known Activations