© 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. 2-RES-MATRYOSHKA-DC
    7. 6346
    Prev
    Next
    INDEX
    Explanations

    explanations related to cross-validation and data partitioning

    oai_token-act-pair · gpt-4.1-nano
    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
    rungsseite
    -0.88
     EconPapers
    -0.76
    uxxxx
    -0.73
    protoimpl
    -0.70
    MigrationBuilder
    -0.69
     مرئيه
    -0.68
    WebElementEntity
    -0.66
    HasAnnotation
    -0.65
    GEBURTSDATUM
    -0.65
     Савезне
    -0.65
    POSITIVE LOGITS
    endforeach
    0.51
    GetBytes
    0.51
    atguigu
    0.49
     grond
    0.47
    GridLayout
    0.46
     Selig
    0.45
    unuz
    0.43
     ChromeDriver
    0.43
     Hentet
    0.43
    rovnik
    0.42
    Activations Density 0.816%

    No Known Activations