© 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. 96521
    Prev
    Next
    INDEX
    Explanations

    including

    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
     but
    -0.55
    principalTable
    -0.49
     прошло
    -0.46
     saja
    -0.46
    følge
    -0.44
     Obrador
    -0.44
     solidarité
    -0.43
    Kanpo
    -0.43
    mobileqq
    -0.43
     znan
    -0.43
    POSITIVE LOGITS
    SourceChecksum
    0.91
     withal
    0.77
    DoubleQuotes
    0.77
     a
    0.76
    
    0.73
    VIAF
    0.69
    UnknownFields
    0.69
     obtaining
    0.64
     supplying
    0.63
     selecting
    0.63
    Activations Density 0.002%

    No Known Activations