© 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. 4-CLT-HP
    7. 4707
    Prev
    Next
    INDEX
    Explanations

    introduction to scientific papers

    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
    SourceChecksum
    -1.00
    contentLoaded
    -0.77
    енча
    -0.75
    modelBuilder
    -0.75
     >=",
    -0.72
    BufferException
    -0.71
    mergeFrom
    -0.70
    __":
    -0.68
    انيف
    -0.68
    WillAppear
    -0.67
    POSITIVE LOGITS
     же
    0.49
     
    0.47
     Ravel
    0.47
    vane
    0.47
    vite
    0.46
    siv
    0.43
    eu
    0.42
    ORO
    0.41
    HAV
    0.40
    мат
    0.39
    Activations Density 0.004%

    No Known Activations