Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44497
    Prev
    Next
    INDEX
    Explanations

    best

    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
     most
    -0.81
    largest
    -0.73
    argest
    -0.72
     simplest
    -0.68
     largest
    -0.66
     fastest
    -0.65
     easiest
    -0.65
     widest
    -0.65
     coolest
    -0.64
     terbesar
    -0.63
    POSITIVE LOGITS
     calendriers
    0.49
     momento
    0.47
     preventable
    0.46
    rowse
    0.46
    queryInterface
    0.45
     e
    0.45
    tose
    0.44
     mie
    0.44
    thâu
    0.44
    ↵↵
    0.43
    Activations Density 0.093%

    No Known Activations