© 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. 93612
    Prev
    Next
    INDEX
    Explanations

    events festivals systems

    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
     väli
    -0.52
     usually
    -0.51
     διά
    -0.50
    IndentedString
    -0.50
     يتيمه
    -0.47
    ్రామ
    -0.46
    тератур
    -0.45
    Usually
    -0.45
     typically
    -0.45
    wärts
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.78
    aarrggbb
    0.65
     viewDidLoad
    0.62
     Roskov
    0.62
     eventdata
    0.59
     Italijanski
    0.56
     ujednoznacz
    0.55
     Fair
    0.55
     utafitiHapana
    0.55
    Enllaces
    0.55
    Activations Density 0.001%

    No Known Activations