© 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. 0-RES-MATRYOSHKA-DC
    7. 12213
    Prev
    Next
    INDEX
    Explanations

    references to code compilation and configuration issues

    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
    Rav
    -0.60
    agisse
    -0.60
     Wink
    -0.59
     Rav
    -0.56
    homonymie
    -0.56
    %>
    -0.56
    født
    -0.56
    sizeCache
    -0.54
    //});
    -0.54
    indd
    -0.54
    POSITIVE LOGITS
    CPP
    3.31
     CPP
    2.95
     cpp
    1.10
    forChild
    0.63
    Eloquent
    0.59
    obod
    0.59
    Cpp
    0.57
     declarar
    0.56
    WindowConstants
    0.56
    itinéraire
    0.55
    Activations Density 0.000%

    No Known Activations