© 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. 5-CLT-HP
    7. 4316
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ,
    -0.61
    GEBURTS
    -0.48
    farwyddwr
    -0.41
    RemoveField
    -0.41
    的呢
    -0.40
    țiile
    -0.39
    …,
    -0.38
    ,\,\
    -0.37
    getB
    -0.36
     baga
    -0.36
    POSITIVE LOGITS
    IUrlHelper
    0.77
     ComVisible
    0.74
    exitRule
    0.73
    WebVitals
    0.72
     متعلقه
    0.71
    +#+#
    0.70
    SuspendLayout
    0.69
     Wiktionnaire
    0.67
    spesies
    0.67
    ंदीखरीदारी
    0.66
    Activations Density 0.053%

    No Known Activations