© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 966
    Prev
    Next
    INDEX
    Explanations

    lines of code with comments

    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
     unknownFields
    -0.59
     CURIAM
    -0.54
    TestingModule
    -0.53
     başladı
    -0.52
    TagHelper
    -0.50
     répartition
    -0.50
     humains
    -0.50
     séparation
    -0.50
    Personensuche
    -0.50
    FormTagHelper
    -0.49
    POSITIVE LOGITS
    protoimpl
    0.74
    AndEndTag
    0.62
    MigrationBuilder
    0.62
     وتسجيلات
    0.60
     pyplot
    0.59
     forKey
    0.57
     HttpNotFound
    0.56
    ariste
    0.56
    setVerticalGroup
    0.55
     //
    0.54
    Activations Density 0.509%

    No Known Activations