© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    references to the start or initiation of a sequence or process

    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
    start
    -0.69
    Start
    -0.67
    ciech
    -0.67
    "])
    -0.65
     Start
    -0.64
    START
    -0.63
     lucky
    -0.62
     Starting
    -0.60
     starting
    -0.59
    ETT
    -0.59
    POSITIVE LOGITS
     began
    1.86
     begun
    1.81
    began
    1.69
     begin
    1.64
     begins
    1.63
     Began
    1.55
    begins
    1.48
     Begins
    1.45
     Begin
    1.41
     BEGIN
    1.28
    Activations Density 0.018%

    No Known Activations