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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40822
    Prev
    Next
    INDEX
    Explanations

    fluids

    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
    Great
    -0.86
     Great
    -0.71
    DockStyle
    -0.67
     fluids
    -0.66
    ThroughAttribute
    -0.66
     Fluids
    -0.62
     scrubs
    -0.59
     steder
    -0.55
    invokeLater
    -0.54
     opérés
    -0.54
    POSITIVE LOGITS
    nemouth
    0.62
    ly
    0.60
    ]--;
    0.57
    ement
    0.56
    timately
    0.54
     VizieR
    0.54
    EOUS
    0.53
    ancy
    0.52
    MLLoader
    0.52
    emment
    0.52
    Activations Density 1.542%

    No Known Activations