© 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. 4740
    Prev
    Next
    INDEX
    Explanations

    references to physical structures or buildings

    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
    UrlEncoded
    -0.73
     Buren
    -0.67
     cometh
    -0.66
    greja
    -0.65
    TagHelper
    -0.64
     OkHttpClient
    -0.63
     benzina
    -0.62
    AnchorTagHelper
    -0.62
     تانيه
    -0.62
     façons
    -0.61
    POSITIVE LOGITS
     facilities
    3.55
     facility
    3.39
     Facilities
    3.25
     Facility
    3.19
    facilities
    3.17
    facility
    3.09
    Facilities
    3.08
    Facility
    3.05
     FACILITIES
    3.02
     FACILITY
    2.84
    Activations Density 0.035%

    No Known Activations