© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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
     so
    -0.69
     considered
    -0.52
     in
    -0.52
     thousands
    -0.47
     I
    -0.47
     different
    -0.47
     with
    -0.46
     and
    -0.46
     why
    -0.46
     some
    -0.46
    POSITIVE LOGITS
    +#+
    1.03
     تانيه
    0.90
     BorderSide
    0.88
    ConstraintMaker
    0.79
     وتسجيلات
    0.79
    RegressionTest
    0.78
    #+#
    0.78
    ArrowToggle
    0.77
    oneofs
    0.77
    XmlAccessType
    0.74
    Activations Density 0.015%

    No Known Activations