© 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. 5928
    Prev
    Next
    INDEX
    Explanations

    Noneover

    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
    thâu
    -0.75
    ///</
    -0.65
     المعيارى
    -0.62
    SourceChecksum
    -0.59
    uelle
    -0.55
    IVEREF
    -0.55
     particular
    -0.54
     webdriver
    -0.54
    öns
    -0.54
    pherson
    -0.53
    POSITIVE LOGITS
    ruptedException
    0.59
    
    0.50
     StatefulWidget
    0.50
    SBATCH
    0.47
    lossians
    0.46
    tableFuture
    0.43
     AssemblyProduct
    0.42
    ymce
    0.41
     يتيمه
    0.41
    PMailer
    0.41
    Activations Density 0.001%

    No Known Activations