© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29375
    Prev
    Next
    INDEX
    Explanations

    names and initials of people, possibly authors of academic papers

    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
     are
    -0.52
    gatsby
    -0.47
     both
    -0.47
    poy
    -0.45
    ともに
    -0.45
    共に
    -0.45
    dela
    -0.44
     -
    -0.44
     ver
    -0.44
     were
    -0.43
    POSITIVE LOGITS
    RegressionTest
    1.00
     bezeichneter
    0.95
    ViewFeatures
    0.92
    aarrggbb
    0.84
    AddHtmlAttribute
    0.84
     betweenstory
    0.83
    tagHelperRunner
    0.81
     >=",
    0.80
    WebVitals
    0.78
    ſelf
    0.77
    Activations Density 0.072%

    No Known Activations