© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    speech thought and feeling

    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
    uxxxx
    -0.59
     препратки
    -0.56
     XSS
    -0.56
    extAlignment
    -0.55
     uintptr
    -0.55
    cshtml
    -0.54
     doInBackground
    -0.52
    windowFixed
    -0.51
    RunAsync
    -0.51
    webElementXpaths
    -0.50
    POSITIVE LOGITS
     nowadays
    0.72
     sometimes
    0.67
     today
    0.65
     often
    0.58
     hoje
    0.55
     complaining
    0.52
     сейчас
    0.51
     vandaag
    0.51
     spesso
    0.51
     lately
    0.50
    Activations Density 0.001%

    No Known Activations