© 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. 24741
    Prev
    Next
    INDEX
    Explanations

    references to scientific data and analysis in the context of health or pharmaceuticals

    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
     ivelany
    -1.07
    ValueStyle
    -1.02
     createState
    -1.02
    RenderAtEndOf
    -1.02
     disambiguazione
    -1.01
    IntoConstraints
    -1.00
    StructEnd
    -0.97
     typelib
    -0.96
    keyColumn
    -0.94
    AnimationsModule
    -0.93
    POSITIVE LOGITS
    <eos>
    0.88
     capuche
    0.49
     maroca
    0.46
     Spéc
    0.45
    ata
    0.44
    ↵↵
    0.44
    <h2>
    0.43
     aéri
    0.43
    StringTo
    0.43
     fuir
    0.42
    Activations Density 0.339%

    No Known Activations