© 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. 2-RES-MATRYOSHKA-DC
    7. 4422
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific researcher or author

    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
     mío
    -0.66
    ftagPool
    -0.59
     Mathf
    -0.59
    Museo
    -0.57
     politiet
    -0.57
     mañana
    -0.57
     musée
    -0.56
     manhã
    -0.56
    homonymie
    -0.56
    mounted
    -0.56
    POSITIVE LOGITS
     kasarigan
    0.65
    ANTLR
    0.55
    JsonHelper
    0.53
    TagHelpers
    0.52
    UnsafeEnabled
    0.51
     Administrativna
    0.48
    tagHelperRunner
    0.47
    IDENTAL
    0.47
     AspNetCore
    0.46
     flood
    0.46
    Activations Density 1.713%

    No Known Activations