© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97552
    Prev
    Next
    INDEX
    Explanations

    Research

    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
    WebServlet
    -0.72
    expandindo
    -0.71
    PRNewswire
    -0.70
    SharedDtor
    -0.66
    orianCalendar
    -0.59
    adpleegd
    -0.58
    IUrlHelper
    -0.58
    richTextPanel
    -0.58
    HostException
    -0.57
     Biôgrafia
    -0.57
    POSITIVE LOGITS
     and
    0.80
    templateUrl
    0.51
    ,
    0.48
    MarshalTo
    0.46
     or
    0.46
     quality
    0.45
     report
    0.42
    ことで
    0.42
     gọn
    0.42
    CopyWith
    0.42
    Activations Density 0.035%

    No Known Activations