© 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. 1-CLT-HP
    7. 10115
    Prev
    Next
    INDEX
    Explanations

    lead, ear's context

    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
    -1.24
     Lead
    -1.11
    lead
    -1.09
    Lead
    -1.02
     LEAD
    -0.91
     Leads
    -0.82
     leads
    -0.81
    leads
    -0.75
     led
    -0.74
    Leads
    -0.74
    POSITIVE LOGITS
    numerusform
    0.70
    #+#
    0.70
    GOTREF
    0.65
     AssemblyVersion
    0.64
     &___
    0.62
    getMinutes
    0.62
    basicConfig
    0.60
     invokingState
    0.59
     viewDidLoad
    0.57
    /*
    0.57
    Activations Density 0.525%

    No Known Activations