© 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. 92349
    Prev
    Next
    INDEX
    Explanations

    earthquakes

    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
    InjectAttribute
    -0.69
    OGND
    -0.62
    ViewFeatures
    -0.61
    SourceChecksum
    -0.60
     CreateTagHelper
    -0.57
    pendente
    -0.57
     الاطلاع
    -0.56
     مشين
    -0.55
    الحياه
    -0.51
     AssemblyProduct
    -0.47
    POSITIVE LOGITS
    ніципалі
    0.63
    Datuak
    0.55
    مصادر
    0.54
    isContained
    0.53
    JspWriter
    0.52
     Fuer
    0.51
     uſed
    0.50
    ioutil
    0.49
     Maurizio
    0.49
    wat
    0.48
    Activations Density 0.000%

    No Known Activations