© 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. 1-CLT-HP
    7. 498
    Prev
    Next
    INDEX
    Explanations

    medical tumors aneurysms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aar
    -0.52
    CloseOperation
    -0.51
    ızı
    -0.48
     TestBed
    -0.48
    umel
    -0.47
     vegetales
    -0.47
    balleur
    -0.45
    BeginInit
    -0.44
    atop
    -0.44
    icos
    -0.44
    POSITIVE LOGITS
    下载附件
    0.66
    ValueStyle
    0.65
     الرياضيه
    0.63
     Widodo
    0.59
     EconPapers
    0.59
     '\\;'
    0.59
    TagMode
    0.58
     незавершена
    0.57
     useAppContext
    0.57
    Hochspringen
    0.57
    Activations Density 0.057%

    No Known Activations