© 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. 1-CLT-HP
    7. 15647
    Prev
    Next
    INDEX
    Explanations

    yield

    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
     yield
    -1.14
     Yield
    -1.02
    yield
    -1.00
    Yield
    -0.97
     Yields
    -0.79
     yields
    -0.74
     yielding
    -0.60
    yields
    -0.60
    IELD
    -0.52
     yielded
    -0.52
    POSITIVE LOGITS
     تضيفلها
    0.76
     kasarigan
    0.73
     Normdatei
    0.72
    protoimpl
    0.71
     Milky
    0.69
     виправивши
    0.68
    WireFormatLite
    0.66
    yntaxException
    0.65
     necks
    0.63
     متعلقه
    0.63
    Activations Density 0.144%

    No Known Activations