© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 319
    Prev
    Next
    INDEX
    Explanations

    references to local anesthesia or localized procedures

    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
    featureID
    -0.62
    İstinadlar
    -0.60
     ModelExpression
    -0.58
    hasMoreElements
    -0.58
     Gattung
    -0.56
    AndroidJUnit
    -0.55
    RTLD
    -0.52
    UnusedPrivate
    -0.51
     newBuilder
    -0.49
    IsRequired
    -0.48
    POSITIVE LOGITS
     local
    4.75
    local
    4.50
    Local
    4.28
     Local
    4.25
     LOCAL
    3.97
    LOCAL
    3.73
     locally
    3.55
     lokal
    3.25
     lokalen
    3.25
    locally
    3.20
    Activations Density 0.770%

    No Known Activations