© 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. 3368
    Prev
    Next
    INDEX
    Explanations

    references to the start of mathematical expressions or code blocks

    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
     '
    -0.93
     "
    -0.80
    s
    -0.75
     ‘
    -0.66
    ,
    -0.65
     or
    -0.63
    "
    -0.61
    ↵
    -0.58
     (
    -0.58
     first
    -0.57
    POSITIVE LOGITS
    begin
    2.86
    enumi
    1.66
    AddTagHelper
    1.65
    BEGIN
    1.56
     BEGIN
    1.51
    Begin
    1.50
     Begin
    1.43
    ValueStyle
    1.41
     begin
    1.40
    LEncoder
    1.31
    Activations Density 0.016%

    No Known Activations