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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90485
    Prev
    Next
    INDEX
    Explanations

    flutter

    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
    principalTable
    -0.76
    IndentedString
    -0.73
    InjectAttribute
    -0.72
    ArrowToggle
    -0.69
    EDEFAULT
    -0.68
    getSystemService
    -0.68
    memoized
    -0.67
    OrBuilder
    -0.66
    ])):
    -0.66
    (!__
    -0.66
    POSITIVE LOGITS
    r
    0.78
    y
    0.78
    son
    0.74
    d
    0.74
    ron
    0.73
    ly
    0.71
    n
    0.69
    ness
    0.68
    m
    0.67
    s
    0.67
    Activations Density 1.156%

    No Known Activations