© 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. 31791
    Prev
    Next
    INDEX
    Explanations

    references to medical treatments and experimental protocols

    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
    quelize
    -0.66
     purpoſe
    -0.66
    ">//
    -0.66
     GenerationType
    -0.64
    новниш
    -0.62
    endphp
    -0.62
    CompleteListener
    -0.62
    IntoConstraints
    -0.62
    kusen
    -0.61
    tagext
    -0.61
    POSITIVE LOGITS
     başına
    0.53
    ⓧ
    0.52
    IVEREF
    0.50
     обращения
    0.46
    runApp
    0.43
     emple
    0.41
     gede
    0.41
    arder
    0.40
    рик
    0.39
    migrationBuilder
    0.38
    Activations Density 0.100%

    No Known Activations