© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94326
    Prev
    Next
    INDEX
    Explanations

    hacking

    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
    protoc
    -0.52
     contextLoads
    -0.52
    Numerology
    -0.52
    istoitu
    -0.51
    ніципалі
    -0.50
     <<<<<<<<<<<<<<
    -0.48
    indépendance
    -0.48
    thand
    -0.47
    şiv
    -0.46
    Fotografía
    -0.46
    POSITIVE LOGITS
     surla
    0.65
    RegressionTest
    0.56
    
    0.53
    lyde
    0.51
    kháu
    0.50
    umon
    0.50
    asan
    0.50
    جت
    0.48
    PerformLayout
    0.48
     pageNo
    0.48
    Activations Density 0.002%

    No Known Activations