© 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. 3-RES-MATRYOSHKA-DC
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    capitalized terms used in research publications

    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
    verwijspagina
    -1.16
     Cagliari
    -1.12
    otoro
    -1.09
     Humboldt
    -0.97
    SourceChecksum
    -0.97
     Quora
    -0.93
    सन्दर्भ
    -0.91
     Pattaya
    -0.91
    annica
    -0.89
    XmlAccessorType
    -0.88
    POSITIVE LOGITS
    ,’
    0.79
    ,\
    0.79
     Gio
    0.78
     Schä
    0.78
    ,”
    0.77
    ’
    0.72
    ’,
    0.71
    :”
    0.70
           
    0.69
     Daw
    0.68
    Activations Density 5.873%

    No Known Activations