© 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. 43143
    Prev
    Next
    INDEX
    Explanations

    numbers related to measurements

    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
    tagHelperRunner
    -0.77
    awakeFromNib
    -0.77
    rungsseite
    -0.75
    WebVitals
    -0.73
     EconPapers
    -0.73
     resourceCulture
    -0.72
    новниш
    -0.70
    principalTable
    -0.68
    liothèque
    -0.67
     دیکھیے
    -0.67
    POSITIVE LOGITS
    ↵
    0.62
    .
    0.53
    %
    0.46
     underv
    0.45
    ,
    0.43
     caufe
    0.42
     Omn
    0.42
    e
    0.42
     depic
    0.42
     ftate
    0.42
    Activations Density 0.813%

    No Known Activations