© 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. 5-CLT-HP
    7. 5384
    Prev
    Next
    INDEX
    Explanations

    trading

    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
     exchanged
    -0.56
     exchange
    -0.52
    OpenHelper
    -0.48
    esez
    -0.48
    Попис
    -0.46
     gi
    -0.44
    vP
    -0.44
    ectoria
    -0.43
     change
    -0.42
    >{@
    -0.42
    POSITIVE LOGITS
    makeConstraints
    0.73
     initComponents
    0.67
    хьтан
    0.66
    +#+
    0.66
     StatefulWidget
    0.63
    httphttps
    0.62
    MessageTagHelper
    0.62
    checs
    0.59
     détruire
    0.58
     AssemblyProduct
    0.55
    Activations Density 0.001%

    No Known Activations