© 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. 1-CLT-HP
    7. 14040
    Prev
    Next
    INDEX
    Explanations

    Soccer/Football

    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
    ThroughAttribute
    -0.69
     AssemblyCulture
    -0.65
    SourceChecksum
    -0.64
     propOrder
    -0.60
    ----</
    -0.59
    tonode
    -0.58
    OGND
    -0.57
    PerformLayout
    -0.57
    -------------</
    -0.57
     تعدى
    -0.56
    POSITIVE LOGITS
    Getenv
    0.54
    +:+
    0.54
    ¯¯
    0.45
    pecia
    0.44
    clientY
    0.42
     tø
    0.41
    PyExc
    0.40
     jezik
    0.40
     colleg
    0.40
     Westbrook
    0.40
    Activations Density 0.179%

    No Known Activations