© 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. 5191
    Prev
    Next
    INDEX
    Explanations

    intervention

    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
    GEBURTSDATUM
    -0.65
    BagConstraints
    -0.56
    setVerticalGroup
    -0.54
    CodeAnalysis
    -0.54
    PMailer
    -0.49
    rativa
    -0.49
    styleUrls
    -0.47
    asal
    -0.46
    RTEE
    -0.45
    noscript
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.66
     militar
    0.62
     AssemblyProduct
    0.61
     EconPapers
    0.59
     internal
    0.57
     domestically
    0.57
     bArr
    0.56
     directly
    0.56
     in
    0.56
     Jovi
    0.55
    Activations Density 0.002%

    No Known Activations