© 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. 2662
    Prev
    Next
    INDEX
    Explanations

    motivation

    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
     CreateTagHelper
    -0.76
    发表于
    -0.72
    şiv
    -0.69
    PreferredItem
    -0.68
    GEBURTSDATUM
    -0.66
    WebVitals
    -0.65
    PerformLayout
    -0.64
    ]='\
    -0.63
    WriteTagHelper
    -0.62
    IndentedString
    -0.61
    POSITIVE LOGITS
     to
    0.96
     for
    0.67
     and
    0.57
     للاسماء
    0.54
     riservata
    0.47
     να
    0.46
     próprios
    0.46
     onPostExecute
    0.45
     toward
    0.44
     potrebné
    0.44
    Activations Density 0.001%

    No Known Activations