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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 695
    Prev
    Next
    INDEX
    Explanations

    geographical features

    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
    Cordialement
    -0.64
    StoryboardSegue
    -0.60
     ivelany
    -0.60
    PyExc
    -0.59
     initComponents
    -0.57
    ()?;
    -0.57
     @"/
    -0.54
    ViewFeatures
    -0.54
    iNdEx
    -0.54
    ostringstream
    -0.53
    POSITIVE LOGITS
    Архівовано
    0.60
    Биография
    0.56
    ########.
    0.54
     Hetero
    0.54
    boca
    0.53
    وض
    0.52
    BeginContext
    0.51
    참고
    0.50
    XmlType
    0.50
     Tami
    0.50
    Activations Density 0.002%

    No Known Activations