© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94165
    Prev
    Next
    INDEX
    Explanations

    neoplasms

    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
    ArrowToggle
    -0.70
    diging
    -0.55
     okuyayım
    -0.53
    berdayakan
    -0.51
     EconPapers
    -0.50
    MemoryWarning
    -0.50
    cumin
    -0.50
     &___
    -0.49
    ThroughAttribute
    -0.49
     propOrder
    -0.49
    POSITIVE LOGITS
    ia
    0.76
    ias
    0.75
    m
    0.73
    ms
    0.72
     NSCoder
    0.62
    IA
    0.61
    IAS
    0.61
    ium
    0.58
    ías
    0.52
    IAA
    0.51
    Activations Density 0.003%

    No Known Activations