© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 368
    Prev
    Next
    INDEX
    Explanations

    descriptions of food or recipes

    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.24.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.24.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
    SequentialGroup
    -0.82
     مرئيه
    -0.73
     vastaan
    -0.71
     quæ
    -0.69
     تانيه
    -0.66
    expandindo
    -0.64
     Möbel
    -0.63
    RegistryLite
    -0.62
    urende
    -0.61
     Poincaré
    -0.60
    POSITIVE LOGITS
     cooked
    0.94
     delicious
    0.94
     flavored
    0.93
     tasted
    0.91
     fresh
    0.89
     flavor
    0.89
     flavorful
    0.88
     savory
    0.86
     tastes
    0.85
     roasted
    0.85
    Activations Density 1.359%

    No Known Activations