© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42174
    Prev
    Next
    INDEX
    Explanations

    of and the

    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
    ]--;
    -0.66
    multirow
    -0.65
     Exactos
    -0.64
     @"/
    -0.60
     Study
    -0.58
    IUrlHelper
    -0.58
     propOrder
    -0.58
     '{@
    -0.54
     AssemblyProduct
    -0.52
    XmlAccessorType
    -0.52
    POSITIVE LOGITS
    раздо
    0.56
     للمعارف
    0.56
     dévelo
    0.55
     ddelweddau
    0.54
    колай
    0.53
     avoient
    0.52
     químicas
    0.52
     initComponents
    0.49
     enfans
    0.49
     fernández
    0.48
    Activations Density 0.215%

    No Known Activations