© 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. 1847
    Prev
    Next
    INDEX
    Explanations

    numeric characters

    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
    TestingModule
    -0.62
     ujednoznacz
    -0.59
    BeforeAll
    -0.53
    LayoutPanel
    -0.51
    homonymie
    -0.49
    ViewImports
    -0.49
    rungsseite
    -0.48
    Diweddarwch
    -0.48
    httphttps
    -0.48
    insee
    -0.47
    POSITIVE LOGITS
     initComponents
    0.73
     resourceCulture
    0.55
    +:+
    0.51
    marle
    0.51
    ParallelGroup
    0.51
    guien
    0.51
     ModelExpression
    0.51
    Adverten
    0.50
    peur
    0.50
    UserScript
    0.49
    Activations Density 0.942%

    No Known Activations