© 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. 0-CLT-HP
    7. 42687
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
     once
    -1.00
     [
    -0.90
    once
    -0.68
    )[
    -0.67
    [\
    -0.62
     ["
    -0.61
    Once
    -0.59
     ['
    -0.58
    ：[
    -0.57
     AssemblyTitle
    -0.56
    POSITIVE LOGITS
     ivelany
    0.65
    PasswordEncoder
    0.60
    _();
    0.58
    WithIOException
    0.57
    AndEndTag
    0.56
    (
    0.54
    WebServlet
    0.52
     himo
    0.52
    occasione
    0.52
    wikidata
    0.51
    Activations Density 3.173%

    No Known Activations