© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39910
    Prev
    Next
    INDEX
    Explanations

    reading and time

    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
    IUrlHelper
    -1.07
    Personendaten
    -0.88
     kaynağından
    -0.73
     चीज़ों
    -0.71
     AssemblyProduct
    -0.71
     scene
    -0.70
    المكان
    -0.69
    脚注の使い方
    -0.68
     Baptism
    -0.68
    تقاوى
    -0.68
    POSITIVE LOGITS
    fully
    0.64
    y
    0.55
    a
    0.52
    to
    0.49
    less
    0.49
    i
    0.48
    ans
    0.47
    fulness
    0.47
    anship
    0.46
    able
    0.45
    Activations Density 0.539%

    No Known Activations