© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42471
    Prev
    Next
    INDEX
    Explanations

    lead

    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
     lead
    -2.55
    lead
    -1.71
     Lead
    -1.64
    Lead
    -1.62
     LEAD
    -1.14
     led
    -1.09
     leads
    -1.03
    LEAD
    -0.97
     plomo
    -0.82
     leading
    -0.74
    POSITIVE LOGITS
    ThroughAttribute
    0.81
     electrolysis
    0.73
     evaporator
    0.73
     zircon
    0.71
     newList
    0.70
     bancaria
    0.69
     volcanoes
    0.69
     sulphide
    0.68
     ploughing
    0.67
     actuator
    0.67
    Activations Density 0.059%

    No Known Activations