© 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. 1937
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and related terms used to describe a sequence, hierarchy, or classification

    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
     
    -0.52
     or
    -0.47
    ,
    -0.46
     other
    -0.44
     West
    -0.43
    elta
    -0.43
    enschappe
    -0.42
    nitus
    -0.42
    .
    -0.42
     :
    -0.40
    POSITIVE LOGITS
     Efq
    0.99
     Jefus
    0.97
     myſelf
    0.96
    RenderAtEndOf
    0.95
     itſelf
    0.94
     Theſe
    0.92
     ་་
    0.91
    AddTagHelper
    0.90
    IntoConstraints
    0.90
     Monfieur
    0.90
    Activations Density 1.827%

    No Known Activations