© 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. 94972
    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
     InputDecoration
    -0.82
    AddTagHelper
    -0.75
     correctes
    -0.73
    haustible
    -0.73
     nonUne
    -0.70
    HomeAsUpEnabled
    -0.69
    UnifiedTopology
    -0.69
    HandleFunc
    -0.69
     svým
    -0.67
    GEBURTSDATUM
    -0.67
    POSITIVE LOGITS
     choice
    0.77
     citizenship
    0.60
     origin
    0.54
     residence
    0.53
    choice
    0.52
     nationality
    0.50
     origine
    0.48
     choix
    0.46
     heritage
    0.45
     CHOICE
    0.45
    Activations Density 0.001%

    No Known Activations