© 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. 1-CLT-HP
    4. 1000
    Prev
    Next
    INDEX
    Explanations

    using (code snippets)

    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
    ArrowToggle
    -0.88
    IsMutable
    -0.87
    RegistryLite
    -0.87
     sinners
    -0.83
     anthropologists
    -0.81
     pilgrims
    -0.80
    SharedCtor
    -0.79
    TintMode
    -0.78
     Conductor
    -0.78
     Wikimedijinoj
    -0.78
    POSITIVE LOGITS
    :
    0.66
    '
    0.45
     type
    0.43
     kind
    0.42
     :
    0.42
    an
    0.41
    &
    0.41
     to
    0.41
     An
    0.40
    jun
    0.40
    Activations Density 0.014%

    No Known Activations