© 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. 6874
    Prev
    Next
    INDEX
    Explanations

    references to scientific data reduction processes and analysis techniques

    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
     Majefty
    -0.76
     itſelf
    -0.72
     Shakspeare
    -0.71
     iſt
    -0.68
     Jefus
    -0.68
     Hift
    -0.67
     tiegħek
    -0.67
     ſeveral
    -0.66
     Conſ
    -0.66
     Perſ
    -0.66
    POSITIVE LOGITS
     EconPapers
    0.61
    Personensuche
    0.58
    ]")]
    0.58
    liferay
    0.57
    ContentAlignment
    0.55
    Jereo
    0.54
    RegressionTest
    0.54
    VersionUID
    0.54
    viks
    0.52
     Seeder
    0.51
    Activations Density 0.649%

    No Known Activations