© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13809
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, especially Torres and Baldus

    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
     itſelf
    -0.81
     ſeveral
    -0.75
     ſever
    -0.75
     ſmall
    -0.72
    RenderAtEndOf
    -0.72
     fufficient
    -0.70
     leaſt
    -0.70
     pleaſure
    -0.69
     againſt
    -0.67
     Monfieur
    -0.66
    POSITIVE LOGITS
    `(
    0.65
    ::{
    0.63
     Bald
    0.63
    imals
    0.60
     Gott
    0.59
    titian
    0.59
     Torres
    0.57
    urlencoded
    0.57
    WebElementEntity
    0.57
    vaadin
    0.54
    Activations Density 0.155%

    No Known Activations