© 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. 15451
    Prev
    Next
    INDEX
    Explanations

    mentions of frequently occurring adverse or problematic events, such as side effects or complications

    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
     continuously
    -0.71
     constantly
    -0.70
    Abp
    -0.68
     تضيفلها
    -0.66
     dommage
    -0.65
     continually
    -0.61
    haustible
    -0.60
    issory
    -0.59
    ATORY
    -0.57
     dessus
    -0.56
    POSITIVE LOGITS
     frequent
    2.41
    frequent
    1.98
     Frequent
    1.95
    Frequent
    1.85
     infrequent
    1.04
     frecuente
    0.88
     fréquent
    0.85
     frecuentes
    0.81
    频繁
    0.69
    enterOuterAlt
    0.67
    Activations Density 0.002%

    No Known Activations