© 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. 7003
    Prev
    Next
    INDEX
    Explanations

    references to the magnetic properties and modeling of spin systems, including Hamiltonians and energy calculations

    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
    :✨
    -0.51
    jami
    -0.49
    exitRule
    -0.49
     signal
    -0.48
    Condol
    -0.47
    Super
    -0.46
     ujednoznacz
    -0.46
     intestino
    -0.45
    cut
    -0.44
     Horne
    -0.43
    POSITIVE LOGITS
    RectangleBorder
    0.85
     Wicidata
    0.83
    ьаж
    0.79
    MLLoader
    0.68
    engertian
    0.65
    ChromeDriver
    0.64
    TextAppearance
    0.63
    createServer
    0.62
     periodic
    0.62
     ویکی‌پدیای
    0.62
    Activations Density 1.284%

    No Known Activations