© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    airport

    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
    \{\\
    -0.73
    InjectAttribute
    -0.72
     CreateTagHelper
    -0.71
     quartiere
    -0.67
     skolen
    -0.66
     ModelExpression
    -0.65
    ftagPool
    -0.64
     løpet
    -0.63
     héri
    -0.62
    SpringBootTest
    -0.61
    POSITIVE LOGITS
     lounges
    0.62
     shuttle
    0.60
     security
    0.55
     metal
    0.55
     limo
    0.54
     lounge
    0.53
     bar
    0.52
     ticketing
    0.52
     hotels
    0.51
     VIP
    0.51
    Activations Density 0.004%

    No Known Activations