© 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. 777
    Prev
    Next
    INDEX
    Explanations

    mathematics and scientific analysis

    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
    expandindo
    -0.84
    MessageOf
    -0.81
     kaarangay
    -0.79
     doInBackground
    -0.78
    JspWriter
    -0.78
    elemField
    -0.77
     MainAxisSize
    -0.77
    HasAnnotation
    -0.76
    تقاوى
    -0.76
    ^(@)
    -0.75
    POSITIVE LOGITS
     mar
    0.52
     Go
    0.47
    ял
    0.46
     due
    0.46
     ya
    0.46
    deleteById
    0.44
     Land
    0.44
    ela
    0.44
    ?
    0.44
     did
    0.43
    Activations Density 0.009%

    No Known Activations