© 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. 0-CLT-HP
    7. 95623
    Prev
    Next
    INDEX
    Explanations

    feeder

    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
     feeder
    -0.57
     Jail
    -0.51
     feeders
    -0.48
     Feeder
    -0.47
     Solids
    -0.46
     AssemblyProduct
    -0.46
     goreng
    -0.46
    DoubleQuotes
    -0.45
     linii
    -0.45
     défis
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.72
    IntoConstraints
    0.61
    bounded
    0.61
    enação
    0.60
    
    0.60
    locene
    0.59
    webElementGuid
    0.59
    wares
    0.59
    }`).
    0.58
    IndentedString
    0.58
    Activations Density 0.154%

    No Known Activations