© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74861
    Prev
    Next
    INDEX
    Explanations

    convi

    np_max-act-logits · 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
     Efq
    -0.67
    rawDesc
    -0.66
    LLocation
    -0.64
    ScopeManager
    -0.62
     useDispatch
    -0.61
     ImportError
    -0.60
    CodeAnalysis
    -0.56
    esModule
    -0.56
    NewUrlParser
    -0.56
     whoſe
    -0.56
    POSITIVE LOGITS
    yer
    0.49
    ni
    0.47
    sizeCache
    0.44
    ini
    0.44
    yesha
    0.44
    yes
    0.43
    ye
    0.43
    Eksterne
    0.42
    が発
    0.42
     كمان
    0.41
    Activations Density 0.001%

    No Known Activations