© 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. 287
    Prev
    Next
    INDEX
    Explanations

    English text

    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
     defaultstate
    -0.57
    ftagPool
    -0.54
     estekak
    -0.53
    RegressionTest
    -0.51
    qrstuvwxyz
    -0.51
     CreateTagHelper
    -0.49
    WebVitals
    -0.49
    AutoScaleMode
    -0.48
    ResponseWriter
    -0.47
    ParseTree
    -0.46
    POSITIVE LOGITS
     XL
    0.62
    Бахар
    0.57
    ">—
    0.56
     Klass
    0.55
    SequentialGroup
    0.54
     domo
    0.53
    فحة
    0.52
     SVD
    0.52
     cop
    0.52
     thou
    0.51
    Activations Density 0.002%

    No Known Activations