© 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. 0-CLT-HP
    7. 2015
    Prev
    Next
    INDEX
    Explanations

    {

    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
     we
    -0.54
    [];
    -0.51
    [];
    -0.47
    ipfel
    -0.47
    ing
    -0.47
     K
    -0.47
    stateProvider
    -0.46
     ma
    -0.45
     ju
    -0.45
     TAMBÉM
    -0.45
    POSITIVE LOGITS
     snippetHide
    0.78
    WebServlet
    0.75
    tvguidetime
    0.72
     feroit
    0.71
     pouvoit
    0.71
    DockStyle
    0.66
    webElementGuid
    0.65
    fjspx
    0.64
     réfugi
    0.63
    PreAuthorize
    0.63
    Activations Density 0.439%

    No Known Activations