© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4655
    Prev
    Next
    INDEX
    Explanations

    af

    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
     Dre
    -0.50
    MD
    -0.50
    cud
    -0.49
    幕
    -0.49
    mack
    -0.49
     dre
    -0.49
     lom
    -0.49
    Dre
    -0.49
     seco
    -0.48
    chon
    -0.47
    POSITIVE LOGITS
     raiſ
    0.62
     ujednoznacz
    0.60
    avigation
    0.59
    LabelTagHelper
    0.56
    niająca
    0.56
     JAXBElement
    0.52
    новниш
    0.52
     grève
    0.52
    bibinfo
    0.52
     Zwiebel
    0.52
    Activations Density 0.001%

    No Known Activations