© 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. 94033
    Prev
    Next
    INDEX
    Explanations

    in

    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
    mybatisplus
    -0.71
     intptr
    -0.66
     AssemblyProduct
    -0.61
    Cyfeiriadau
    -0.57
     ModelExpression
    -0.54
    UnusedPrivate
    -0.54
    MessageOf
    -0.52
    енча
    -0.51
    ChildScrollView
    -0.50
    XmlAccessType
    -0.50
    POSITIVE LOGITS
     to
    0.69
     eksper
    0.61
    存于互联网档案馆
    0.56
     fides
    0.56
    itization
    0.56
    Zacks
    0.55
    QRST
    0.55
     this
    0.55
     our
    0.53
    modelBuilder
    0.52
    Activations Density 0.002%

    No Known Activations