© 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. 1-CLT-HP
    7. 13760
    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
    MessageOf
    -0.90
     kasarigan
    -0.82
     NSCoder
    -0.78
    ValueStyle
    -0.76
    AddTagHelper
    -0.76
    PreferredItem
    -0.73
    RectangleBorder
    -0.71
    contentLoaded
    -0.71
    WebElementEntity
    -0.69
    Portale
    -0.67
    POSITIVE LOGITS
     we
    0.61
     consider
    0.55
     podemos
    0.54
     elever
    0.52
    iseksi
    0.51
     mogelijkheden
    0.50
     considerar
    0.50
     förstå
    0.49
     considérer
    0.48
     rayas
    0.48
    Activations Density 0.011%

    No Known Activations