© 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. 40663
    Prev
    Next
    INDEX
    Explanations

    Homes, diagnostics, and newbies

    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
    ThroughAttribute
    -0.93
     فريبيس
    -0.74
    الإنجليزية
    -0.71
    UnsafeEnabled
    -0.64
     Normdatei
    -0.62
     lenker
    -0.60
    abestanden
    -0.60
     виправивши
    -0.59
     propOrder
    -0.59
     autorytatywna
    -0.59
    POSITIVE LOGITS
     &'
    0.52
     RegExp
    0.47
     Reviewer
    0.47
    getMock
    0.46
    AsyncResult
    0.46
    NavigationView
    0.44
     reviewer
    0.43
    ($__
    0.43
    APIView
    0.43
    {"
    0.41
    Activations Density 0.177%

    No Known Activations