© 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. 2928
    Prev
    Next
    INDEX
    Explanations

    cloud

    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
    ScopeManager
    -0.56
    出版年
    -0.54
    NameInMap
    -0.51
    icol
    -0.50
    atory
    -0.50
    XtraReports
    -0.49
     متعلقه
    -0.47
    ValueStyle
    -0.47
    BASEPATH
    -0.46
     segue
    -0.46
    POSITIVE LOGITS
    లాలు
    0.53
     vPvB
    0.53
    InstrumentedTest
    0.52
    ↵↵
    0.50
     Abp
    0.50
    ruptedException
    0.49
    >{@
    0.48
    bitat
    0.47
     comprennent
    0.47
    ">'+
    0.46
    Activations Density 0.001%

    No Known Activations