© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14911
    Prev
    Next
    INDEX
    Explanations

    references to the chemical compound Lac or related substances

    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
    asgi
    -0.60
    blower
    -0.51
    PyExc
    -0.51
    bondale
    -0.50
    EVT
    -0.50
    DAV
    -0.50
    achy
    -0.48
     Steward
    -0.46
    LabelTagHelper
    -0.45
    pertino
    -0.45
    POSITIVE LOGITS
     Lac
    3.17
    Lac
    3.14
     lac
    2.81
    lac
    2.47
     LAC
    1.88
    LAC
    1.78
     lacquer
    1.48
     lacs
    1.13
     lacquered
    1.04
    Datuak
    0.87
    Activations Density 0.000%

    No Known Activations