© 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. 5386
    Prev
    Next
    INDEX
    Explanations

    moment

    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
    RegressionTest
    -0.62
     ctypes
    -0.59
     DriverManager
    -0.57
    Portail
    -0.56
    
    -0.54
    сели
    -0.52
    序
    -0.52
    PhysRevD
    -0.50
    WebRequest
    -0.50
    dolu
    -0.50
    POSITIVE LOGITS
    Demografie
    0.59
     clarity
    0.58
     clearness
    0.54
     claridad
    0.50
     ModelExpression
    0.49
    Clarity
    0.48
     unplanned
    0.45
     Clarity
    0.45
    aneous
    0.43
    aneously
    0.42
    Activations Density 0.001%

    No Known Activations