© 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. 5-CLT-HP
    7. 94296
    Prev
    Next
    INDEX
    Explanations

    to

    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
    
    -0.59
    kháu
    -0.51
    AddTagHelper
    -0.51
     qualitatively
    -0.50
     competitively
    -0.50
     Completely
    -0.49
    AddHtmlAttribute
    -0.49
     completely
    -0.47
     NSCoder
    -0.47
     COMPLE
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    InputBorder
    0.60
     intersections
    0.58
    Spoljašnje
    0.58
     plates
    0.54
    ToMany
    0.52
     portals
    0.52
    riezmann
    0.50
     Ouvrez
    0.50
     highways
    0.50
    Activations Density 0.005%

    No Known Activations