© 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. 12202
    Prev
    Next
    INDEX
    Explanations

    warnings

    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
     warning
    -0.81
     Warning
    -0.69
    ScopeManager
    -0.69
    NavController
    -0.65
    WebServlet
    -0.62
     warnings
    -0.61
     WARNING
    -0.61
     autorytatywna
    -0.60
     BrowserModule
    -0.59
     Warnings
    -0.58
    POSITIVE LOGITS
     bells
    0.57
     bell
    0.51
     CascadeType
    0.48
    INDICATOR
    0.47
     civili
    0.47
     cytok
    0.47
    requestCode
    0.45
    queryInterface
    0.45
    clearance
    0.44
    getDeclared
    0.44
    Activations Density 0.004%

    No Known Activations