© 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. 6698
    Prev
    Next
    INDEX
    Explanations

    references to luxury products and related concepts

    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
     nôtre
    -0.85
     feroit
    -0.81
     vélos
    -0.76
     transférez
    -0.75
     mairie
    -0.75
     auroit
    -0.73
     poitrine
    -0.73
     soeur
    -0.73
     colère
    -0.72
     armée
    -0.72
    POSITIVE LOGITS
     luxury
    1.64
     Luxury
    1.48
     luxurious
    1.45
    Luxury
    1.45
    luxury
    1.38
     luxe
    1.25
    Lux
    1.23
     VIP
    1.19
     lux
    1.16
     elegant
    1.16
    Activations Density 1.023%

    No Known Activations