© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    pation

    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
    th
    -0.65
    eski
    -0.53
    thard
    -0.52
    zuführen
    -0.50
    setz
    -0.49
    tham
    -0.47
    gins
    -0.47
     but
    -0.45
     perut
    -0.45
     langkah
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.83
    ViewImports
    0.82
    InjectAttribute
    0.82
    SharedDtor
    0.77
     typhoid
    0.75
     invariants
    0.75
     Vivaldi
    0.74
     Shakspeare
    0.74
     Daß
    0.73
    SpringBootTest
    0.72
    Activations Density 0.072%

    No Known Activations