© 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. 5-CLT-HP
    7. 91591
    Prev
    Next
    INDEX
    Explanations

    Parenthesis

    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
    RegressionTest
    -0.80
     AssemblyVersion
    -0.79
     ProtoMessage
    -0.78
    writeFieldEnd
    -0.78
     '\\;'
    -0.74
     <",
    -0.72
    KommentareTeilen
    -0.71
    addCriterion
    -0.70
    NgModule
    -0.68
    Xna
    -0.68
    POSITIVE LOGITS
    a
    0.60
    one
    0.59
    (
    0.57
    ones
    0.56
    "
    0.52
    an
    0.52
    temi
    0.50
    -
    0.49
    or
    0.48
    poli
    0.48
    Activations Density 0.000%

    No Known Activations