© 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. 6161
    Prev
    Next
    INDEX
    Explanations

    references to eigenvalues and eigenvectors in mathematical and physical 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
     Mittelpunkt
    -0.62
     متعلقه
    -0.61
     Huk
    -0.60
    jdons
    -0.60
     referenties
    -0.58
     Référence
    -0.57
     digitais
    -0.57
     Mercurio
    -0.57
    drücke
    -0.56
     empf
    -0.56
    POSITIVE LOGITS
     Eigen
    2.86
     eigen
    2.83
    Eigen
    2.73
    eigen
    2.56
     eigenvalues
    2.02
     eigenvectors
    1.97
     eigenvalue
    1.95
     eig
    1.24
    eig
    1.19
    Eig
    1.08
    Activations Density 0.004%

    No Known Activations