© 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. 90975
    Prev
    Next
    INDEX
    Explanations

    tee

    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
    ed
    -0.88
     printing
    -0.60
     Shakspeare
    -0.60
     fevere
    -0.59
     sırt
    -0.56
     matters
    -0.56
     mounting
    -0.56
     sleeping
    -0.55
     Nacionales
    -0.54
     severe
    -0.54
    POSITIVE LOGITS
    Personensuche
    0.79
    WebElementEntity
    0.71
    RegistryLite
    0.70
    PerformLayout
    0.67
    GEBURTSDATUM
    0.64
    IContainer
    0.60
     Paglinawan
    0.60
    twimg
    0.58
    ServletException
    0.56
    sightly
    0.56
    Activations Density 0.153%

    No Known Activations