© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1858
    Prev
    Next
    INDEX
    Explanations

    and

    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
    PRNewswire
    -0.53
    ::<
    -0.49
    ########.
    -0.48
    <caption>
    -0.47
    shows
    -0.46
     surla
    -0.45
    poir
    -0.45
    IContainer
    -0.45
    WebKit
    -0.45
    ]--;
    -0.45
    POSITIVE LOGITS
     to
    1.47
     for
    0.91
     improve
    0.86
     increase
    0.73
     protect
    0.71
     prevent
    0.70
     achieve
    0.69
     prepare
    0.69
     provide
    0.69
     compensate
    0.69
    Activations Density 0.012%

    No Known Activations