© 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. 0-RES-MATRYOSHKA-DC
    7. 12986
    Prev
    Next
    INDEX
    Explanations

    references to the researcher Lind in various contexts

    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
    DockStyle
    -0.78
    ThroughAttribute
    -0.70
     resourceCulture
    -0.59
     integrable
    -0.57
     Réponses
    -0.55
    IntoConstraints
    -0.55
    verwijspagina
    -0.54
     Borel
    -0.54
    EndGlobalSection
    -0.53
    émoc
    -0.52
    POSITIVE LOGITS
     holomorphic
    1.53
     Lind
    1.10
    Lind
    0.93
     Herman
    0.84
    Herman
    0.76
     lind
    0.72
     Martha
    0.71
    Martha
    0.70
    RectangleBorder
    0.60
    migrationBuilder
    0.57
    Activations Density 0.002%

    No Known Activations