© 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. 5-CLT-HP
    7. 94011
    Prev
    Next
    INDEX
    Explanations

    Alaska

    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
    Искәрмәләр
    -0.71
     Roskov
    -0.62
    WaitGroup
    -0.61
     AssemblyCulture
    -0.60
    enumii
    -0.55
    DockStyle
    -0.54
    archiviato
    -0.53
    +:+
    -0.53
    preduce
    -0.53
    DispatchToProps
    -0.52
    POSITIVE LOGITS
    TintMode
    0.56
    RegistryLite
    0.52
    memoized
    0.51
     Teen
    0.47
     Circuits
    0.47
     Technic
    0.47
     Tef
    0.46
     Pies
    0.46
     Site
    0.45
     Adult
    0.45
    Activations Density 0.001%

    No Known Activations