© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93844
    Prev
    Next
    INDEX
    Explanations

    useful

    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
     المعيارى
    -0.63
     שוליים
    -0.61
     خارجية
    -0.52
    ोटो
    -0.47
    WinForms
    -0.47
    passing
    -0.47
    p
    -0.47
     informée
    -0.46
    ted
    -0.45
    ki
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.58
    __*/
    0.58
     economic
    0.55
    ItemBackground
    0.52
    ?>">
    0.51
    ergic
    0.50
     econ
    0.50
    órmula
    0.49
    conomie
    0.48
    انيف
    0.48
    Activations Density 0.010%

    No Known Activations