© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39925
    Prev
    Next
    INDEX
    Explanations

    usefulness

    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
    ever
    -0.58
     betweenstory
    -0.57
    epiece
    -0.56
    XmlAccessType
    -0.55
     kasarigan
    -0.54
     AssemblyCulture
    -0.54
    weds
    -0.52
     resourceCulture
    -0.51
     geslacht
    -0.50
     vormen
    -0.50
    POSITIVE LOGITS
     not
    0.70
     to
    0.67
     for
    0.66
     only
    0.62
     chiefly
    0.61
     primarily
    0.61
     mostly
    0.60
     mainly
    0.60
    >",
    0.58
     inasmuch
    0.58
    Activations Density 0.058%

    No Known Activations