© 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. 0-CLT-HP
    7. 38410
    Prev
    Next
    INDEX
    Explanations

    mutable/coated

    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
    invokeLater
    -0.73
     width
    -0.70
    inducing
    -0.58
    width
    -0.56
    Width
    -0.54
    coated
    -0.52
    onAttach
    -0.52
    edos
    -0.51
    ComponentScan
    -0.48
     precedes
    -0.48
    POSITIVE LOGITS
    IVEREF
    0.77
    sizeCache
    0.77
     médec
    0.72
     leçons
    0.71
     banques
    0.69
     snippetHide
    0.68
     grève
    0.68
     aikaa
    0.68
     églises
    0.68
     gouvernements
    0.67
    Activations Density 0.321%

    No Known Activations