© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13477
    Prev
    Next
    INDEX
    Explanations

    sequences of digits with stylized formatting indicating test results or statistical significance

    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
    ,
    -0.63
     respectively
    -0.58
    .
    -0.57
    ;
    -0.53
    日閲覧
    -0.52
     whose
    -0.51
     altogether
    -0.51
     The
    -0.51
    AnchorTagHelper
    -0.51
     scena
    -0.49
    POSITIVE LOGITS
    <<<<
    0.81
    wiſe
    0.78
     EconPapers
    0.73
     pageContext
    0.73
    varlak
    0.73
     ?...
    0.71
     esternos
    0.71
     DST
    0.70
    × 
    0.70
     Superan
    0.70
    Activations Density 0.073%

    No Known Activations