© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92005
    Prev
    Next
    INDEX
    Explanations

    s

    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
    SourceChecksum
    -1.17
    Autoritní
    -1.15
     AssemblyCulture
    -1.06
    TagMode
    -0.94
     ModelExpression
    -0.93
    ScopeManager
    -0.93
     initComponents
    -0.92
    ItemBackground
    -0.91
    +#+#
    -0.91
    ValueStyle
    -0.88
    POSITIVE LOGITS
     lasting
    0.39
     resulta
    0.38
     amely
    0.38
     gian
    0.37
     dring
    0.34
     occupy
    0.31
     než
    0.31
     ocurre
    0.31
     decir
    0.30
     lasts
    0.30
    Activations Density 0.002%

    No Known Activations