© 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. 15631
    Prev
    Next
    INDEX
    Explanations

    references to type 2 diabetes

    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
     purpoſe
    -0.74
     poffe
    -0.74
     pleaſure
    -0.72
     uſe
    -0.68
     reaſon
    -0.68
     enfans
    -0.67
     quæ
    -0.65
     Monfieur
    -0.65
     preſent
    -0.63
     againſt
    -0.61
    POSITIVE LOGITS
     estimés
    0.68
    bootstrapcdn
    0.66
    joba
    0.62
     defaultstate
    0.61
    참고
    0.61
    uxxxx
    0.60
    ỡng
    0.60
     cherchés
    0.59
    不着
    0.59
    medriver
    0.58
    Activations Density 0.002%

    No Known Activations