© 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. 4-CLT-HP
    7. 4900
    Prev
    Next
    INDEX
    Explanations

    complexity/chaos

    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
    JspWriter
    -0.75
     виправивши
    -0.75
     propOrder
    -0.72
    ]")]
    -0.71
     AssemblyTitle
    -0.70
     Мексичка
    -0.69
    __':
    -0.68
    indakan
    -0.68
    dymyr
    -0.67
    AndEndTag
    -0.66
    POSITIVE LOGITS
     picture
    0.67
     AssemblyCompany
    0.60
     road
    0.55
     mix
    0.54
     path
    0.54
     history
    0.52
     web
    0.51
    autoconfigure
    0.49
     relationship
    0.48
     record
    0.48
    Activations Density 0.003%

    No Known Activations