© 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. 5903
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific or technical entities, especially names and classifications of fossils, tumors, and geographical regions

    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
     vectorielles
    -0.82
    IsContent
    -0.71
    <bos>
    -0.69
     étions
    -0.63
    WebVitals
    -0.60
    woordig
    -0.60
     forcé
    -0.59
     testé
    -0.59
    AxisAlignment
    -0.57
    sendRedirect
    -0.57
    POSITIVE LOGITS
    GEBURTSDATUM
    0.69
    ViewFeatures
    0.65
    æus
    0.63
    <_>
    0.57
    Portály
    0.56
    unteer
    0.55
    плек
    0.54
     intptr
    0.54
    <()>
    0.54
     وتسجيلات
    0.54
    Activations Density 1.384%

    No Known Activations