© 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. 92791
    Prev
    Next
    INDEX
    Explanations

    start

    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
    ,
    -0.81
    .
    -0.62
    :
    -0.54
    ino
    -0.50
     (
    -0.50
     :
    -0.50
    ;
    -0.49
     to
    -0.48
    ric
    -0.48
    念
    -0.46
    POSITIVE LOGITS
     שוליים
    0.88
    webElementXpaths
    0.88
     الرياضيه
    0.84
    OGND
    0.82
     ujednoznacz
    0.81
     kasarigan
    0.81
     saites
    0.79
    PreferredItem
    0.78
     estekak
    0.77
     nahilalakip
    0.76
    Activations Density 0.001%

    No Known Activations