© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5639
    Prev
    Next
    INDEX
    Explanations

    references to and measurements of lattice 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
    StoryboardSegue
    -0.70
     peindre
    -0.67
    GEBURTSDATUM
    -0.63
    FormTagHelper
    -0.59
    Jokes
    -0.58
     spedizione
    -0.58
    SourceChecksum
    -0.58
     resolução
    -0.57
    /**
    -0.57
     transfé
    -0.56
    POSITIVE LOGITS
     lattice
    3.19
     Lattice
    2.75
    lattice
    2.66
    Lattice
    2.50
     lattices
    2.48
    格子
    1.05
     trellis
    0.95
     решет
    0.90
     grid
    0.81
    gitter
    0.77
    Activations Density 0.006%

    No Known Activations