© 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. 3-RES-MATRYOSHKA-DC
    7. 1094
    Prev
    Next
    INDEX
    Explanations

    words with strong emotional connotations, typically negative

    oai_token-act-pair · gemini-2.0-flash
    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
    reportWebVitals
    -0.85
    WebVitals
    -0.70
     kasarigan
    -0.66
     ujednoznacz
    -0.61
     verru
    -0.61
    StoreMessageInfo
    -0.60
    مند
    -0.58
    RegistryLite
    -0.58
    serviceWorker
    -0.57
    Билгалдахарш
    -0.56
    POSITIVE LOGITS
     anger
    1.06
     humility
    0.97
     optimism
    0.91
     compassion
    0.89
     Anger
    0.88
     indignation
    0.87
    siasme
    0.86
     patience
    0.86
     sympathy
    0.83
     frustration
    0.83
    Activations Density 2.089%

    No Known Activations