© 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. 75270
    Prev
    Next
    INDEX
    Explanations

    code/math

    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
     in
    -0.49
    ode
    -0.48
     or
    -0.47
     that
    -0.45
     
    -0.43
     will
    -0.42
     step
    -0.42
    ↵↵
    -0.41
    us
    -0.41
    ®
    -0.41
    POSITIVE LOGITS
    __*/
    1.04
     ExecuteAsync
    1.04
    RenderAtEndOf
    0.93
    rawDesc
    0.88
    Portale
    0.88
     estekak
    0.86
    таратура
    0.86
     propOrder
    0.85
    SharedDtor
    0.84
    makeText
    0.84
    Activations Density 0.016%

    No Known Activations