© 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. 2-RES-MATRYOSHKA-DC
    7. 2806
    Prev
    Next
    INDEX
    Explanations

    references to the trace or tracing in scientific or technical contexts

    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
     beginnetje
    -1.04
     autorytatywna
    -1.00
    AlterField
    -0.94
     photolibrary
    -0.94
    IsContent
    -0.93
     itſelf
    -0.93
     raiſ
    -0.93
     ſche
    -0.90
    windowFixed
    -0.90
     Roskov
    -0.90
    POSITIVE LOGITS
     trace
    3.58
    trace
    3.11
     Trace
    3.05
     traces
    3.02
    Trace
    2.92
     Traces
    2.67
    traces
    2.58
    Traces
    2.48
     TRACE
    2.36
     traced
    2.34
    Activations Density 0.014%

    No Known Activations