© 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. 4-CLT-HP
    7. 279
    Prev
    Next
    INDEX
    Explanations

    and

    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
    帖最后由
    -0.75
    AndEndTag
    -0.74
     propOrder
    -0.73
     autorytatywna
    -0.69
     hendes
    -0.68
     betweenstory
    -0.68
    AccessorTable
    -0.66
    RegressionTest
    -0.66
    RegistryLite
    -0.65
     للاسماء
    -0.62
    POSITIVE LOGITS
    ,
    0.68
     can
    0.67
     will
    0.57
     whether
    0.57
     Can
    0.56
     may
    0.54
     on
    0.53
     cannot
    0.52
     which
    0.52
     the
    0.50
    Activations Density 0.003%

    No Known Activations