© 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. 4-CLT-HP
    7. 717
    Prev
    Next
    INDEX
    Explanations

    but

    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
    writeFieldEnd
    -0.59
     متعلقه
    -0.57
    __":
    -0.51
    WithMany
    -0.50
     typelib
    -0.50
     excellence
    -0.48
     Rodrig
    -0.48
    PRNewswire
    -0.46
    lente
    -0.46
    kule
    -0.45
    POSITIVE LOGITS
    Hentet
    0.61
     todavía
    0.54
    AddTagHelper
    0.54
     linkovi
    0.54
     and
    0.54
    âmara
    0.54
    rotum
    0.53
     still
    0.52
     يتيمه
    0.52
     likewise
    0.51
    Activations Density 0.010%

    No Known Activations