© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1680
    Prev
    Next
    INDEX
    Explanations

    stream

    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
    stream
    -1.08
     Stream
    -1.05
    STREAM
    -0.98
    Streaming
    -0.97
     STREAM
    -0.96
    Stream
    -0.96
     streamed
    -0.93
    steam
    -0.86
    streaming
    -0.86
     streamer
    -0.84
    POSITIVE LOGITS
     للمعارف
    1.11
    TypedDataSet
    0.90
    Autoritní
    0.90
     ویکی‌پدی
    0.81
     utafitiHapana
    0.78
    onAttach
    0.76
    RegistryLite
    0.74
    aarrggbb
    0.73
     typelib
    0.73
    évaluateur
    0.73
    Activations Density 0.490%

    No Known Activations