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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14080
    Prev
    Next
    INDEX
    Explanations

    sequences indicating the temporal occurrence of events or actions

    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
    DockStyle
    -0.68
    Geplaatst
    -0.67
    Билгалдахарш
    -0.62
     current
    -0.61
     gyhoeddwyd
    -0.60
     Subsequently
    -0.59
    URBANA
    -0.58
     referenties
    -0.56
     khiển
    -0.55
    RouterModule
    -0.52
    POSITIVE LOGITS
     thereafter
    2.59
     Thereafter
    2.16
     Daarna
    0.88
    Ther
    0.87
     hereafter
    0.82
     suivantes
    0.81
     henceforth
    0.81
     itſelf
    0.79
     automatiques
    0.77
     leçon
    0.72
    Activations Density 0.002%

    No Known Activations