© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96627
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     تضيفلها
    -0.73
    andExpect
    -0.64
    principalTable
    -0.55
     Paglinawan
    -0.54
     SEDS
    -0.54
    μφωνα
    -0.52
     Asegúrese
    -0.52
    Personensuche
    -0.49
    mandu
    -0.49
    Халык
    -0.49
    POSITIVE LOGITS
    vois
    0.54
    ніципалі
    0.51
    okolade
    0.49
    jelder
    0.49
    قایناقلار
    0.49
     cassettes
    0.48
    precious
    0.47
    ismer
    0.46
     Brink
    0.46
     kasarigan
    0.46
    Activations Density 0.000%

    No Known Activations