© 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. 25830
    Prev
    Next
    INDEX
    Explanations

    references to dietary practices and their effects

    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
     QtWidgets
    -0.72
    ventricular
    -0.71
     nakalista
    -0.66
    agulation
    -0.66
     Chwiliwch
    -0.66
    UALA
    -0.64
    enderror
    -0.63
    ofday
    -0.63
    nextProps
    -0.61
    PRESENT
    -0.61
    POSITIVE LOGITS
     diet
    1.00
    diet
    0.94
     DIET
    0.92
     diets
    0.91
     Diet
    0.88
     Dietrich
    0.86
    Diet
    0.82
     dietary
    0.75
    PhysRevD
    0.73
     Sadie
    0.71
    Activations Density 0.011%

    No Known Activations