© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20438
    Prev
    Next
    INDEX
    Explanations

    references to the study of medical conditions related to headaches and healthcare workers

    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
    Negative Logits
    idopsis
    -0.78
     EClass
    -0.77
     actionMode
    -0.76
    featureID
    -0.75
     ویکی‌پدی
    -0.75
    SOUNDBITE
    -0.74
     lenker
    -0.72
    addCriterion
    -0.71
     <=",
    -0.68
    ngilizce
    -0.67
    POSITIVE LOGITS
     distribuzione
    0.52
     bassi
    0.52
    find
    0.47
     Survey
    0.47
     attre
    0.46
     Study
    0.46
     estudio
    0.44
    Study
    0.44
    dasarkan
    0.44
    Survey
    0.43
    Activations Density 0.339%

    No Known Activations