© 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. 2-RES-MATRYOSHKA-DC
    7. 6840
    Prev
    Next
    INDEX
    Explanations

    mentions of specific plant-derived ingredients or food components, particularly various nuts, herbs, vegetables, and fruits

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     animals
    -0.79
     Animals
    -0.78
    Animals
    -0.77
     Италијани
    -0.76
     الحره
    -0.73
    GeneratedCode
    -0.71
     animal
    -0.70
    ToScroll
    -0.70
     مواليد
    -0.69
    animals
    -0.68
    POSITIVE LOGITS
     tomato
    1.35
     grape
    1.26
     Tomato
    1.21
     cherry
    1.18
     tomatoes
    1.16
     strawberry
    1.15
     olive
    1.13
     apple
    1.13
     potato
    1.10
     Grape
    1.10
    Activations Density 0.571%

    No Known Activations