© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96222
    Prev
    Next
    INDEX
    Explanations

    data

    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
     AssemblyCompany
    -0.65
    WebElementEntity
    -0.52
    AutoresizingMask
    -0.49
    MutableLiveData
    -0.49
    EMOS
    -0.49
    iores
    -0.48
    gettimeofday
    -0.48
    AttributeSet
    -0.47
     IV
    -0.47
     onOptions
    -0.47
    POSITIVE LOGITS
     to
    0.71
    apimachinery
    0.67
    CppMethod
    0.64
     correspondiente
    0.59
     maintained
    0.56
     ***!
    0.56
    niająca
    0.55
    bootstrapcdn
    0.55
     Maintaining
    0.54
     quiser
    0.52
    Activations Density 0.003%

    No Known Activations