© 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. 1-CLT-HP
    7. 45796
    Prev
    Next
    INDEX
    Explanations

    Watkins

    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
     Watkins
    -0.94
    patrick
    -0.70
     CURIAM
    -0.65
    Rhestr
    -0.58
    cycline
    -0.57
    Smarty
    -0.56
    \{\\
    -0.55
    URLException
    -0.51
    anglès
    -0.51
    asky
    -0.51
    POSITIVE LOGITS
    UnusedPrivate
    0.72
    Personendaten
    0.57
    /***/
    0.52
    Contributors
    0.50
     ffilm
    0.49
     performance
    0.49
     kaarangay
    0.48
     jScrollPane
    0.48
     שוליים
    0.48
     Italijani
    0.47
    Activations Density 0.026%

    No Known Activations