© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    a combination of common characters used in academic publications, math and unicode text

    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
     sanguí
    -0.57
     cardíaca
    -0.53
     grafica
    -0.49
     désigner
    -0.47
     Diagram
    -0.47
     видит
    -0.46
    lė
    -0.45
    UnitTesting
    -0.45
    vstack
    -0.45
     zien
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.80
     Paglinawan
    0.73
    skjaer
    0.71
    Hentet
    0.70
     disambiguazione
    0.70
    ⁩
    0.66
     الدولى
    0.65
    IsMutable
    0.63
    RegressionTest
    0.63
     EconPapers
    0.62
    Activations Density 1.469%

    No Known Activations