Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14786
    Prev
    Next
    INDEX
    Explanations

    sequences of time-related events or timers

    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
    featureID
    -0.94
     Timer
    -0.93
    PerformLayout
    -0.88
     timers
    -0.88
     BoxFit
    -0.87
     חיצוניים
    -0.84
    parsedMessage
    -0.83
     متعلقه
    -0.81
     nakalista
    -0.81
    setVerticalGroup
    -0.79
    POSITIVE LOGITS
    timer
    1.95
    tell
    0.50
     Gesells
    0.50
    ,
    0.47
    $_.
    0.45
    teln
    0.45
    ers
    0.44
     Dienst
    0.44
    Attrs
    0.44
     mineral
    0.43
    Activations Density 0.002%

    No Known Activations