© 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. 1-CLT-HP
    7. 11665
    Prev
    Next
    INDEX
    Explanations

    technical/medical texts

    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
     diagonally
    -1.19
     diagonal
    -0.95
    strophy
    -0.93
     Diagonal
    -0.85
    Diagonal
    -0.81
    diagonal
    -0.70
     ويكيميديا
    -0.57
    IndentedString
    -0.56
    tgz
    -0.55
     diagon
    -0.53
    POSITIVE LOGITS
    الحياه
    0.57
    izable
    0.56
    @[+][
    0.54
    　　《
    0.53
    MLLoader
    0.53
    izations
    0.52
    MemoryWarning
    0.52
    ніципалі
    0.51
     '\\;'
    0.50
     vPvB
    0.50
    Activations Density 0.004%

    No Known Activations