© 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. 15303
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual's name within a context, particularly "Uan" or "Hawk."

    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
     ple
    -1.23
     Ple
    -0.73
     suction
    -0.67
     kasarigan
    -0.65
     Suction
    -0.59
     незавершена
    -0.59
    tvguidetime
    -0.58
    تقاوى
    -0.58
     chi
    -0.56
    Ple
    -0.54
    POSITIVE LOGITS
    hawk
    1.76
    uan
    1.73
    hawks
    1.70
    Hawk
    1.34
     Hawk
    1.24
    Hawks
    1.20
    UAN
    1.16
     hawks
    1.14
     hawk
    1.10
     Hawks
    1.07
    Activations Density 0.003%

    No Known Activations