© 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. 4-CLT-HP
    7. 1884
    Prev
    Next
    INDEX
    Explanations

    that

    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
     مرئيه
    -0.63
    ạy
    -0.59
    RTLD
    -0.58
     contextLoads
    -0.57
     AssemblyCulture
    -0.56
    WithMany
    -0.52
    hésite
    -0.52
    itects
    -0.52
     étions
    -0.52
    endregion
    -0.51
    POSITIVE LOGITS
     newBuilder
    0.61
    tvguidetime
    0.60
     referenties
    0.60
     will
    0.49
     ivelany
    0.49
    fits
    0.46
    cupa
    0.45
     ofs
    0.44
    帖最后由
    0.44
     stands
    0.43
    Activations Density 0.006%

    No Known Activations