© 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. 0-RES-MATRYOSHKA-DC
    7. 11957
    Prev
    Next
    INDEX
    Explanations

    references to the hospitality industry

    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
     compliments
    -1.02
     compliment
    -1.00
    compli
    -0.92
     Compli
    -0.82
     complimented
    -0.74
    Compli
    -0.66
     complimentary
    -0.62
     Hecht
    -0.57
     scolaire
    -0.57
     merit
    -0.56
    POSITIVE LOGITS
     hospitality
    2.08
    Hospitality
    1.80
     Hospitality
    1.77
    hospital
    1.22
     hospitable
    0.97
    iddle
    0.90
     deference
    0.75
    ParseException
    0.65
    ospital
    0.64
    IContainer
    0.61
    Activations Density 0.004%

    No Known Activations