© 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. 92541
    Prev
    Next
    INDEX
    Explanations

    creation, modification

    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
    
    -0.79
     الحره
    -0.77
     recently
    -0.74
     récents
    -0.74
     متعلقه
    -0.71
    recently
    -0.71
    HasAnnotation
    -0.70
    XmlAccessType
    -0.69
    principalColumn
    -0.68
     jScrollPane
    -0.67
    POSITIVE LOGITS
     each
    0.67
     every
    0.60
    ỗi
    0.59
     daily
    0.59
     everyday
    0.55
    $\\
    0.52
    each
    0.51
     EACH
    0.50
     setiap
    0.50
     chaque
    0.49
    Activations Density 0.153%

    No Known Activations