© 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. 4-CLT-HP
    7. 4490
    Prev
    Next
    INDEX
    Explanations

    choice

    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
    GEBURTSDATUM
    -1.07
    oredCriteria
    -0.81
    PerformLayout
    -0.76
     choosing
    -0.72
    Autoritní
    -0.70
    CppCodeGen
    -0.69
    choosing
    -0.68
    errHandler
    -0.68
     betweenstory
    -0.66
     choices
    -0.66
    POSITIVE LOGITS
     for
    0.96
     для
    0.54
     untuk
    0.53
     of
    0.50
    for
    0.49
     as
    0.48
     برای
    0.48
     mainly
    0.47
     커
    0.47
     für
    0.46
    Activations Density 0.012%

    No Known Activations