© 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. 6170
    Prev
    Next
    INDEX
    Explanations

    references to skin conditions, treatments, or procedures

    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
     hair
    -0.62
     arras
    -0.59
    Hair
    -0.58
     hairdresser
    -0.57
    urface
    -0.56
     Hage
    -0.56
     Hair
    -0.56
    hair
    -0.54
    appen
    -0.54
    💈
    -0.53
    POSITIVE LOGITS
     skin
    3.50
     Skin
    3.14
    skin
    3.05
    Skin
    2.92
     SKIN
    2.84
     skins
    2.75
    SKIN
    2.56
    skins
    2.36
     Skins
    2.36
     peau
    2.23
    Activations Density 0.011%

    No Known Activations