© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6077
    Prev
    Next
    INDEX
    Explanations

    :

    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
    Negative Logits
    transQ
    -0.80
     Waray
    -0.75
    GeneratedMessage
    -0.70
    VIAF
    -0.69
    PreferredItem
    -0.69
    Extinguishing
    -0.68
     المعيارى
    -0.61
    hup
    -0.60
    ыгана
    -0.60
    ViewFeatures
    -0.60
    POSITIVE LOGITS
     @
    0.46
    ylem
    0.41
    </h2>
    0.41
     Wang
    0.40
    glers
    0.40
    InjectAttribute
    0.40
     Rodrig
    0.39
    Lähteet
    0.38
     '{@
    0.37
    ADATA
    0.37
    Activations Density 0.006%

    No Known Activations