© 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. 3838
    Prev
    Next
    INDEX
    Explanations

    patterns related to diagonal matrix structures

    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
     متعلقه
    -0.80
     שוליים
    -0.78
    Personensuche
    -0.78
    :✨
    -0.71
     Aristotle
    -0.70
     ProtoMessage
    -0.69
     calendriers
    -0.69
     transfieras
    -0.69
     Monfieur
    -0.67
     Turquía
    -0.66
    POSITIVE LOGITS
     diagonal
    3.25
    diagonal
    3.00
    Diagonal
    2.53
     Diagonal
    2.45
     diagonals
    2.14
     diagon
    2.02
     diagonally
    1.73
    diag
    1.28
     diag
    1.21
    Diag
    1.10
    Activations Density 0.004%

    No Known Activations