© 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. 0-RES-MATRYOSHKA-DC
    7. 14379
    Prev
    Next
    INDEX
    Explanations

    references to specific medical terminology or technical identifiers

    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
     mắn
    -0.54
    IENT
    -0.52
    AddTagHelper
    -0.52
    confirmButton
    -0.51
    LEGGI
    -0.51
     araw
    -0.51
    UseVisualStyle
    -0.50
    FACTS
    -0.50
    chenkt
    -0.50
     Weh
    -0.49
    POSITIVE LOGITS
    idio
    3.42
     Idio
    2.30
     idio
    1.88
    Idio
    1.87
     idiom
    1.31
     idioms
    1.30
    ídio
    0.82
    idios
    0.82
    IDI
    0.71
     idiots
    0.68
    Activations Density 0.001%

    No Known Activations