© 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. 0-CLT-HP
    7. 42646
    Prev
    Next
    INDEX
    Explanations

    K/Yard

    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
    K
    -1.42
     K
    -1.23
     Yard
    -0.93
     yard
    -0.91
     k
    -0.85
    k
    -0.83
     yards
    -0.82
    Ｋ
    -0.79
    Yard
    -0.77
     Yards
    -0.74
    POSITIVE LOGITS
    iness
    0.52
    lı
    0.50
    olas
    0.49
    vägen
    0.47
    ages
    0.46
    ness
    0.45
    hver
    0.45
    hip
    0.44
    iest
    0.44
    ly
    0.44
    Activations Density 0.148%

    No Known Activations