© 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. 22-RES-MATRYOSHKA-DC
    7. 2945
    Prev
    Next
    INDEX
    Explanations

    references to unhealthy food

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    +:+
    -0.87
    ьаж
    -0.71
     nahilalakip
    -0.70
     Himo
    -0.70
     OFDb
    -0.66
     nutritious
    -0.65
     ostavi
    -0.63
    queryInterface
    -0.63
     meal
    -0.62
    LookAnd
    -0.62
    POSITIVE LOGITS
     processed
    0.74
     junk
    0.69
     Processed
    0.68
     fast
    0.62
    processed
    0.61
     refined
    0.60
     Refined
    0.58
     sugar
    0.57
     Fast
    0.56
     artificial
    0.56
    Activations Density 0.236%

    No Known Activations