© 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. 0-CLT-HP
    7. 92235
    Prev
    Next
    INDEX
    Explanations

    total

    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
    MemoryWarning
    -0.66
    lapsingToolbar
    -0.66
     виправивши
    -0.66
     cherchés
    -0.64
    ureusement
    -0.59
    ſelf
    -0.59
     Paglinawan
    -0.59
    følgelig
    -0.59
    posób
    -0.57
     simplifié
    -0.57
    POSITIVE LOGITS
     of
    1.34
     number
    0.67
     amount
    0.66
     view
    0.63
     approach
    0.62
    of
    0.61
     multitude
    0.61
     set
    0.56
     effort
    0.56
     combination
    0.56
    Activations Density 0.088%

    No Known Activations