© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    present tense verbs ending in 'ing', particularly in scientific contexts

    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
    gence
    -0.59
     reported
    -0.57
    ষ্
    -0.56
     etre
    -0.56
    ellation
    -0.55
    haul
    -0.54
    isia
    -0.54
    astia
    -0.54
    Становништво
    -0.53
     extensive
    -0.52
    POSITIVE LOGITS
     kasarigan
    0.80
     reproducing
    0.79
     trier
    0.71
    IUrlHelper
    0.71
    MLLoader
    0.69
    disposing
    0.65
    bayaran
    0.64
    Protecting
    0.64
     umane
    0.64
     infecting
    0.64
    Activations Density 0.884%

    No Known Activations