© 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. 1-CLT-HP
    7. 15611
    Prev
    Next
    INDEX
    Explanations

    corruption

    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
     corrupt
    -0.63
    posedge
    -0.57
    basicConfig
    -0.57
    elo
    -0.53
     BufferedWriter
    -0.50
     useStyles
    -0.49
     corruption
    -0.48
     Obispo
    -0.47
     /\.(
    -0.46
    ImageContext
    -0.46
    POSITIVE LOGITS
    webElementXpaths
    0.60
    windowFixed
    0.59
    EndProject
    0.56
    Jereo
    0.55
     autorytatywna
    0.54
     göre
    0.54
     nahilalakip
    0.54
    ofern
    0.53
    ambilan
    0.53
    oa̍t
    0.51
    Activations Density 0.073%

    No Known Activations