© 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. 2086
    Prev
    Next
    INDEX
    Explanations

    department

    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
    الإنجليزية
    -0.72
    <bos>
    -0.59
    ’
    -0.55
     $
    -0.52
     at
    -0.48
    HC
    -0.47
    weih
    -0.47
    here
    -0.47
    ájá
    -0.47
    áját
    -0.45
    POSITIVE LOGITS
    TagMode
    0.81
     متعلقه
    0.73
     المعيارى
    0.71
    DockStyle
    0.65
    DispatchToProps
    0.63
    PositiveButton
    0.62
    InjectAttribute
    0.62
    TestingModule
    0.60
     ArrayAdapter
    0.59
     EconPapers
    0.59
    Activations Density 0.005%

    No Known Activations