© 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. 96111
    Prev
    Next
    INDEX
    Explanations

    world, nation

    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
    HasForeignKey
    -0.73
    Personendaten
    -0.70
     الرياضيه
    -0.67
    SharedDtor
    -0.66
    RegistryLite
    -0.65
    basicConfig
    -0.65
    parsedMessage
    -0.65
    లాలు
    -0.64
    MockMvc
    -0.63
    LookAnd
    -0.62
    POSITIVE LOGITS
    ’
    0.54
     widest
    0.50
     lightest
    0.48
     largest
    0.45
     biggest
    0.42
     counterpart
    0.42
    ̵
    0.41
     reference
    0.41
     heaviest
    0.40
     highest
    0.40
    Activations Density 0.004%

    No Known Activations