© 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. 6-RES-MATRYOSHKA-DC
    7. 733
    Prev
    Next
    INDEX
    Explanations

    scientific reports

    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
     typelib
    -0.81
    IndentedString
    -0.76
    DrawerToggle
    -0.69
    StoryboardSegue
    -0.67
    ChildIndex
    -0.66
     beginnetje
    -0.65
    Viited
    -0.63
    Enllaces
    -0.63
    ProcessEvent
    -0.61
     Wikimedijinoj
    -0.61
    POSITIVE LOGITS
     indisponible
    0.52
    PAPER
    0.50
     study
    0.49
     vidare
    0.47
     thiệu
    0.46
    ここでは
    0.46
     بيها
    0.43
    Paper
    0.43
    RSpec
    0.43
     därför
    0.43
    Activations Density 1.965%

    No Known Activations