© 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. 10365
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific, code

    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
    Personendaten
    -0.68
     hat
    -0.52
     breakthrough
    -0.50
    Parcelize
    -0.49
    FormTagHelper
    -0.48
     aç
    -0.48
    Хьажоргаш
    -0.48
     caps
    -0.48
     camp
    -0.47
    LabelTagHelper
    -0.46
    POSITIVE LOGITS
     محفوظة
    0.72
    ########.
    0.70
    IsContent
    0.66
     jajaja
    0.64
     Paglinawan
    0.59
     épaules
    0.59
    tagext
    0.58
    JspWriter
    0.56
     váll
    0.56
     helft
    0.56
    Activations Density 0.291%

    No Known Activations