© 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. 23164
    Prev
    Next
    INDEX
    Explanations

    terms related to cooking and kitchenware

    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
    stateProvider
    -0.96
     Hadid
    -0.79
    Ursula
    -0.74
    memberId
    -0.73
     Zad
    -0.71
    routeProvider
    -0.69
     viewType
    -0.69
    Autoritní
    -0.69
    Personensuche
    -0.68
     DIA
    -0.68
    POSITIVE LOGITS
     Cook
    1.72
     COOK
    1.53
    Cook
    1.48
    cook
    1.38
     Cooks
    1.37
     cook
    1.36
     Cooke
    1.27
    COOK
    1.23
     cooking
    1.09
     Cooking
    1.08
    Activations Density 0.010%

    No Known Activations