© 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. 95150
    Prev
    Next
    INDEX
    Explanations

    of

    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
    DockStyle
    -0.77
    AndEndTag
    -0.76
    NOPQRST
    -0.70
     postIndex
    -0.65
    鰭
    -0.62
    ArrowToggle
    -0.61
    dü
    -0.61
     doGet
    -0.57
     @"/
    -0.56
    клопе
    -0.56
    POSITIVE LOGITS
     expression
    0.56
     texts
    0.52
     text
    0.51
     data
    0.50
    Искәрмәләр
    0.49
     komunikasi
    0.48
     myself
    0.47
     discourse
    0.46
     language
    0.46
     media
    0.46
    Activations Density 0.001%

    No Known Activations