© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4470
    Prev
    Next
    INDEX
    Explanations

    references to air duct systems in a home

    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
     HQ
    -0.47
    oko
    -0.46
    ipi
    -0.43
     transfert
    -0.42
     Farley
    -0.42
    ijen
    -0.41
    .
    -0.40
    komend
    -0.40
     juger
    -0.39
    .~(\
    -0.39
    POSITIVE LOGITS
    ARCHITECT
    0.93
     termites
    0.93
     drywall
    0.90
     architectural
    0.89
    Architectural
    0.89
    Furniture
    0.88
     roofs
    0.88
    Plumbing
    0.85
     uſed
    0.84
     furniture
    0.83
    Activations Density 1.133%

    No Known Activations