© 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. 4-CLT-HP
    7. 3038
    Prev
    Next
    INDEX
    Explanations

    potential

    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
    WebVitals
    -0.71
    saraba
    -0.63
    prepareStatement
    -0.63
    はじめに
    -0.62
     autorytatywna
    -0.58
    SPATH
    -0.57
    WaitGroup
    -0.56
     CreateTagHelper
    -0.55
    chend
    -0.54
     /\.
    -0.53
    POSITIVE LOGITS
     to
    0.96
     majeur
    0.65
    ähteet
    0.62
     argint
    0.61
     fût
    0.57
    tiéndose
    0.57
     RIPRODUZIONE
    0.57
     vänner
    0.55
     zelve
    0.55
    nemies
    0.54
    Activations Density 0.003%

    No Known Activations