© 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. 90536
    Prev
    Next
    INDEX
    Explanations

    single

    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
     single
    -2.16
     Single
    -1.75
    single
    -1.65
    Single
    -1.49
     $
    -1.45
     SINGLE
    -1.44
    SINGLE
    -1.30
     singles
    -1.07
    单
    -0.98
    シングル
    -0.93
    POSITIVE LOGITS
     HasFactory
    0.80
    +#+#
    0.75
    Билгалдахарш
    0.74
    GEBURTS
    0.74
    NUMX
    0.73
     المعيارى
    0.72
    
    0.71
     AssemblyCompany
    0.70
    readystatechange
    0.70
    ControllerAdvice
    0.70
    Activations Density 1.717%

    No Known Activations