© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16171
    Prev
    Next
    INDEX
    Explanations

    computers and electronics

    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
    Negative Logits
    charge
    -0.50
     sar
    -0.48
     charge
    -0.44
    dri
    -0.44
    ืน
    -0.43
     
    -0.43
     distribution
    -0.42
     b
    -0.40
     rango
    -0.40
     trí
    -0.40
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.86
     CreateTagHelper
    0.85
     propOrder
    0.84
    IntoConstraints
    0.84
     <=",
    0.81
    AddTagHelper
    0.78
    +:+
    0.74
     विश्वसनीयता
    0.72
     nakalista
    0.72
     estekak
    0.71
    Activations Density 0.056%

    No Known Activations