© 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. 94721
    Prev
    Next
    INDEX
    Explanations

    varied writing contexts

    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
    it
    -0.52
    fieldLabel
    -0.50
    lloworld
    -0.46
    他有
    -0.42
    ньому
    -0.40
    It
    -0.39
     geslacht
    -0.39
     неё
    -0.39
     chiesto
    -0.38
     něm
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    setVerticalGroup
    0.82
     the
    0.73
    CloseOperation
    0.70
     LoggerFactory
    0.69
    TestingModule
    0.69
     AssemblyProduct
    0.67
    AndEndTag
    0.66
    BeginContext
    0.64
     a
    0.63
    Activations Density 0.001%

    No Known Activations