© 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. 0-CLT-HP
    7. 45592
    Prev
    Next
    INDEX
    Explanations

    fragmented specific topics

    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
     estekak
    -0.68
    setVerticalGroup
    -0.68
     VIAF
    -0.60
     [*]
    -0.56
    éné
    -0.56
     betweenstory
    -0.56
     ویکی‌پدیا
    -0.54
    Espèce
    -0.53
    Nazionale
    -0.52
    viewmodel
    -0.52
    POSITIVE LOGITS
    '
    0.64
    ’
    0.64
     Infórmanos
    0.55
    发表于
    0.54
     wants
    0.54
    fully
    0.52
    :✨
    0.51
     picado
    0.51
    Trama
    0.50
    Demografia
    0.47
    Activations Density 0.015%

    No Known Activations