© 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. 0-CLT-HP
    7. 41532
    Prev
    Next
    INDEX
    Explanations

    one

    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
     one
    -0.57
     my
    -0.55
    ↵
    -0.52
     their
    -0.50
     Compile
    -0.50
     being
    -0.48
    Compile
    -0.48
    setWindow
    -0.48
    <eos>
    -0.48
     Cook
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.88
     '\\;'
    0.88
     spéciaux
    0.77
     autorité
    0.73
     prossima
    0.71
     parachoque
    0.69
     preocupes
    0.69
     étrangère
    0.69
     prochaine
    0.68
    harusnya
    0.67
    Activations Density 0.045%

    No Known Activations