© 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. 5-CLT-HP
    7. 4628
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    참고
    -0.48
      (
    -0.48
    iau
    -0.47
    הערות
    -0.46
     lutte
    -0.45
     getRule
    -0.45
    //</
    -0.44
     G
    -0.44
    Jeden
    -0.44
     schre
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.73
    InputTagHelper
    0.66
    HideFlags
    0.57
     समीक्षक
    0.54
     ROK
    0.53
     tolerably
    0.53
    nappropriate
    0.51
    LabelTagHelper
    0.50
     unconditional
    0.50
    Surprise
    0.50
    Activations Density 0.002%

    No Known Activations