© 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. 1-CLT-HP
    7. 46255
    Prev
    Next
    INDEX
    Explanations

    researchers

    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
    BeginContext
    -0.85
     Roskov
    -0.78
     AssemblyVersion
    -0.73
    хьтан
    -0.72
    WriteTagHelper
    -0.71
     AssemblyCulture
    -0.69
    "],
    -0.69
    SequentialGroup
    -0.69
    "}";
    -0.69
     متعلقه
    -0.69
    POSITIVE LOGITS
     are
    0.46
     there
    0.41
     Wikipedia
    0.40
     provato
    0.39
    φα
    0.39
    Cho
    0.39
    cea
    0.39
     mandatario
    0.39
     verden
    0.39
     performed
    0.38
    Activations Density 0.066%

    No Known Activations