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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91483
    Prev
    Next
    INDEX
    Explanations

    )

    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
     di
    -0.52
    reportWebVitals
    -0.50
    ParallelGroup
    -0.49
    嘧
    -0.48
    menea
    -0.46
    olphins
    -0.44
    hyo
    -0.43
    chier
    -0.43
     CreateTagHelper
    -0.43
     intptr
    -0.42
    POSITIVE LOGITS
    ponses
    0.60
     wireType
    0.58
    例句
    0.57
    出版年
    0.56
    fromnode
    0.56
    !
    0.55
     nonatomic
    0.54
    InSection
    0.54
    Tikang
    0.54
    
    0.54
    Activations Density 0.003%

    No Known Activations