© 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. 12-RES-MATRYOSHKA-DC
    7. 28409
    Prev
    Next
    INDEX
    Explanations

    references to the carotid artery

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ized
    -0.66
     fuoco
    -0.57
     Minas
    -0.57
     يتيمه
    -0.54
    aneamente
    -0.54
    Vader
    -0.54
    sise
    -0.54
     Theſe
    -0.54
    rH
    -0.54
    ật
    -0.53
    POSITIVE LOGITS
     carotid
    1.70
     Caro
    1.29
    Caro
    1.08
     calendriers
    0.77
    caro
    0.77
     taps
    0.73
    UrlResolution
    0.71
    PreferredItem
    0.69
    iolis
    0.69
     AssemblyCulture
    0.68
    Activations Density 0.000%

    No Known Activations