© 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. 3-RES-MATRYOSHKA-DC
    7. 2101
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to topology and analysis

    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
     OFDb
    -0.75
    Datuak
    -0.73
    LookAnd
    -0.73
    GEBURTSDATUM
    -0.71
     صوتيه
    -0.66
    queryInterface
    -0.64
    ăsp
    -0.64
     تضيفلها
    -0.63
     Roskov
    -0.63
     pinulongan
    -0.62
    POSITIVE LOGITS
    electrode
    0.54
     pylab
    0.53
    MessageTagHelper
    0.52
     Charts
    0.52
    ándolos
    0.50
    ideration
    0.50
     neighborhood
    0.50
    phazard
    0.49
    INCLUDED
    0.49
    Charts
    0.48
    Activations Density 0.407%

    No Known Activations