© 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. 31869
    Prev
    Next
    INDEX
    Explanations

    mentions of dietary supplements and related terms

    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
     Deak
    -0.77
    smoke
    -0.70
     Rockefeller
    -0.69
     Houd
    -0.65
     Rani
    -0.63
     kn
    -0.63
     Kuro
    -0.62
    routeProvider
    -0.62
     Joh
    -0.61
     Lied
    -0.61
    POSITIVE LOGITS
     supplement
    1.30
     supplements
    1.26
     supplemented
    1.20
     Supplement
    1.17
     supplementing
    1.15
    Supplement
    1.12
    supplement
    1.09
     Supplements
    1.07
     SUPPLEMENT
    1.02
     supplementation
    1.01
    Activations Density 0.009%

    No Known Activations