© 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. 92266
    Prev
    Next
    INDEX
    Explanations

    Importance/Value

    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
    ándola
    -0.71
     InputDecoration
    -0.69
    AddHtmlAttribute
    -0.67
     estimés
    -0.65
     (
    -0.65
    ándome
    -0.62
    rungsseite
    -0.60
     (
    -0.60
     дописавши
    -0.59
    ConstraintMaker
    -0.59
    POSITIVE LOGITS
     and
    0.59
     “
    0.52
     "
    0.52
    argout
    0.48
    ,
    0.47
    出版年
    0.45
     missing
    0.45
    ngdoc
    0.43
    openzeppelin
    0.43
     thing
    0.43
    Activations Density 0.007%

    No Known Activations