© 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. 28690
    Prev
    Next
    INDEX
    Explanations

    mentions of ingredients in various contexts

    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
    thâu
    -0.85
    ControllerTest
    -0.85
     Wikimedijinoj
    -0.85
     <>",
    -0.81
     Pavia
    -0.80
     contextLoads
    -0.79
    AccessFile
    -0.77
    Diwedd
    -0.76
    Sklici
    -0.75
     userList
    -0.75
    POSITIVE LOGITS
     ingredients
    1.55
     Ingredients
    1.47
     Ingredient
    1.46
    Ingredients
    1.38
     ingredient
    1.30
     INGREDIENTS
    1.29
    ingredients
    1.27
    Ingredient
    1.21
     ingredi
    1.20
    ingredient
    1.18
    Activations Density 0.007%

    No Known Activations