© 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. 31149
    Prev
    Next
    INDEX
    Explanations

    references to the National Institutes of Health (NIH) and related health institutions

    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
    érienne
    -0.55
     conta
    -0.54
    يات
    -0.52
    on
    -0.50
     Kunden
    -0.50
     cases
    -0.49
    дви
    -0.48
    </code>
    -0.48
    anton
    -0.48
    ⋮
    -0.48
    POSITIVE LOGITS
     NIH
    1.62
    NIH
    1.35
     nih
    0.96
     lenker
    0.96
     Institutes
    0.96
    nih
    0.93
    LEncoder
    0.91
     Nih
    0.89
    hesda
    0.86
     Bethesda
    0.85
    Activations Density 0.004%

    No Known Activations