Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4048
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    SharedDtor
    -0.64
    WithIOException
    -0.63
     typelib
    -0.62
     betweenstory
    -0.57
    queryInterface
    -0.55
    Tikang
    -0.54
    TestingModule
    -0.53
     متعلقه
    -0.52
    spender
    -0.52
     AssemblyCulture
    -0.50
    POSITIVE LOGITS
     Integr
    0.56
     Dí
    0.52
    Inte
    0.51
     Bassi
    0.50
    ख्य
    0.50
    yeli
    0.50
     Khusus
    0.50
    }]
    
    0.49
     Vek
    0.49
     Oppen
    0.49
    Activations Density 0.020%

    No Known Activations