© 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. 4356
    Prev
    Next
    INDEX
    Explanations

    references to food-related items and cooking

    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
     ever
    -1.16
    Ever
    -1.07
     jamás
    -1.05
     jamais
    -1.04
     EVER
    -1.02
    ever
    -1.01
     Ever
    -0.98
     seldom
    -0.94
    EVER
    -0.94
     rarely
    -0.90
    POSITIVE LOGITS
     always
    2.44
    always
    2.22
     Always
    2.11
    Always
    1.98
     siempre
    1.69
     altijd
    1.61
     ALWAYS
    1.61
     sempre
    1.55
     всегда
    1.52
     alway
    1.52
    Activations Density 0.017%

    No Known Activations