© 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. 11371
    Prev
    Next
    INDEX
    Explanations

    references to professional massage therapy and related services

    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
     occupied
    -0.71
    EndGlobalSection
    -0.66
     onOptions
    -0.62
     diaphragm
    -0.61
    adaptiveStyles
    -0.59
    CloseOperation
    -0.59
     fung
    -0.57
     endblock
    -0.57
    cule
    -0.57
    AddTagHelper
    -0.56
    POSITIVE LOGITS
     massage
    1.45
     Massage
    1.30
    Massage
    1.23
     massages
    1.08
     occupants
    1.04
    massage
    0.98
     occupant
    0.88
     Occupancy
    0.86
     occupancy
    0.81
     masaje
    0.78
    Activations Density 0.003%

    No Known Activations