© 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. 2792
    Prev
    Next
    INDEX
    Explanations

    Introductions

    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
     atypical
    -0.59
     Alger
    -0.56
     intermediates
    -0.55
    labili
    -0.54
     analogies
    -0.52
     lente
    -0.52
     imputation
    -0.52
     computations
    -0.51
     contemporaine
    -0.51
    :][
    -0.50
    POSITIVE LOGITS
    VersionUID
    0.54
    érfi
    0.54
    存于互联网档案馆
    0.54
    Välislingid
    0.52
    basicConfig
    0.52
    iastical
    0.51
    PhysRevLett
    0.51
    endphp
    0.49
    ajuku
    0.49
    toBeDefined
    0.49
    Activations Density 0.003%

    No Known Activations