© 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. 6-RES-MATRYOSHKA-DC
    7. 1185
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and electromagnetism, identifying scientific discourse

    oai_token-act-pair · gemini-2.0-flash
    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
    ettbewer
    -0.70
    SpringBootTest
    -0.61
    ittens
    -0.59
     maximal
    -0.57
     چقدر
    -0.57
     Taktlose
    -0.57
     Brandt
    -0.57
     Lokales
    -0.57
     Numerology
    -0.57
     maximum
    -0.55
    POSITIVE LOGITS
     BoxDecoration
    0.79
     AssemblyTitle
    0.66
    Trama
    0.65
    RenderAtEndOf
    0.59
    MENAFN
    0.57
    //
    0.56
    \{\\
    0.56
     InputDecoration
    0.54
    MLLoader
    0.54
     tebal
    0.53
    Activations Density 1.446%

    No Known Activations