© 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. 14994
    Prev
    Next
    INDEX
    Explanations

    PCA

    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
     gez
    -0.47
    MEAS
    -0.45
     DMS
    -0.44
    SizeMode
    -0.44
     Dingen
    -0.44
    gez
    -0.42
    ciaż
    -0.42
    vij
    -0.42
     Below
    -0.41
     velkommen
    -0.41
    POSITIVE LOGITS
    twimg
    0.97
     Paglinawan
    0.95
    HasForeignKey
    0.85
     kasarigan
    0.80
     مرئيه
    0.77
    webElementXpaths
    0.75
    OGND
    0.71
     onCreateView
    0.68
    adpleegd
    0.68
     knex
    0.68
    Activations Density 0.022%

    No Known Activations