© 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. 4672
    Prev
    Next
    INDEX
    Explanations

    references to very short time intervals or durations measured in the nanosecond to microsecond range

    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
     kaynağından
    -0.62
     düzen
    -0.47
     perdere
    -0.45
     léč
    -0.44
    postmedia
    -0.44
    I
    -0.44
     despedida
    -0.43
     comienzan
    -0.42
     antigas
    -0.42
    ihin
    -0.42
    POSITIVE LOGITS
     seconds
    1.43
     Seconds
    1.37
    Seconds
    1.23
    seconds
    1.16
     milliseconds
    1.12
     SECON
    1.09
     Sekunden
    1.02
     giây
    0.99
     segundos
    0.98
     secondes
    0.95
    Activations Density 0.284%

    No Known Activations