© 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. 43741
    Prev
    Next
    INDEX
    Explanations

    odyne

    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
    odyne
    -0.96
     Мексичка
    -0.60
    InputBorder
    -0.59
    DockStyle
    -0.58
    medriver
    -0.55
     GenerationType
    -0.54
    GEBURTS
    -0.54
    stateMutability
    -0.53
     استنادى
    -0.52
    mybatisplus
    -0.50
    POSITIVE LOGITS
    ism
    0.67
     Trix
    0.65
     photolibrary
    0.63
     charité
    0.63
     prière
    0.61
    er
    0.60
     fevere
    0.60
     salivary
    0.60
     Plutarch
    0.60
    erent
    0.59
    Activations Density 0.037%

    No Known Activations