© 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. 91865
    Prev
    Next
    INDEX
    Explanations

    Multiplicative comparisons, percentages

    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
     ujednoznacz
    -0.77
     وتسجيلات
    -0.77
     Оно
    -0.65
     absten
    -0.65
     विश्वसनीयता
    -0.65
     fidé
    -0.64
     ControllerBase
    -0.61
    Dislikes
    -0.60
     समीक्षाओं
    -0.60
     quæ
    -0.58
    POSITIVE LOGITS
     as
    0.57
     taller
    0.52
     larger
    0.52
     bigger
    0.51
     longer
    0.51
    kloped
    0.50
     MessageBoxIcon
    0.48
    randomUUID
    0.47
    RemoteException
    0.47
     članak
    0.47
    Activations Density 0.001%

    No Known Activations