© 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. 5-CLT-HP
    7. 2171
    Prev
    Next
    INDEX
    Explanations

    how

    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
    <bos>
    -0.76
     CreateTagHelper
    -0.62
    الإنجليزية
    -0.57
    AddHtmlAttribute
    -0.55
     للاسماء
    -0.51
    arraycopy
    -0.50
     gynnwys
    -0.49
     autorytatywna
    -0.48
    RemindMe
    -0.48
     viime
    -0.46
    POSITIVE LOGITS
    migrationBuilder
    0.77
    XmlAccessType
    0.62
    SpringRunner
    0.61
    Portály
    0.59
    iac
    0.59
     BoxDecoration
    0.56
    oes
    0.56
    ÊN
    0.56
     that
    0.55
    berge
    0.55
    Activations Density 0.003%

    No Known Activations