© 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. 5327
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     is
    -0.54
     offers
    -0.52
     same
    -0.51
    .
    -0.51
     has
    -0.51
     works
    -0.50
     “
    -0.49
     Sau
    -0.49
     fo
    -0.48
     presented
    -0.48
    POSITIVE LOGITS
    expandindo
    0.86
    setViewportView
    0.77
    AndEndTag
    0.75
     tartalomajánló
    0.74
    addCriterion
    0.74
     فريبيس
    0.70
    الحياه
    0.69
     AssemblyCompany
    0.69
    webElementXpaths
    0.68
    AddTagHelper
    0.67
    Activations Density 0.005%

    No Known Activations