© 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. 29650
    Prev
    Next
    INDEX
    Explanations

    words indicating categories or groupings

    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
     divide
    -0.50
    divider
    -0.49
    ::::::::
    -0.48
    безпе
    -0.47
     split
    -0.46
     Приступљено
    -0.46
    BackStack
    -0.46
     between
    -0.45
     سرد
    -0.44
    erover
    -0.43
    POSITIVE LOGITS
    FormTagHelper
    0.86
    ❋
    0.73
     beginnetje
    0.71
    AnchorTagHelper
    0.68
     Chwiliwch
    0.68
    цездатний
    0.68
     propOrder
    0.63
     igång
    0.63
     Flä
    0.63
    κια
    0.63
    Activations Density 0.089%

    No Known Activations