© 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. 96463
    Prev
    Next
    INDEX
    Explanations

    legal and formal

    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
    SourceChecksum
    -0.95
    MERCIAL
    -0.68
     صوتيه
    -0.67
    IBLIO
    -0.66
     OnInit
    -0.66
     Jefus
    -0.65
    CodedInputStream
    -0.63
     đây
    -0.63
     fubject
    -0.63
    Искәрмәләр
    -0.62
    POSITIVE LOGITS
    NDC
    0.42
    offsetof
    0.41
     coloré
    0.39
    SD
    0.39
     pardoned
    0.38
     chilen
    0.37
     <<<<<<<<<<<<<<
    0.37
     conservé
    0.37
    cshtml
    0.36
    ViewImports
    0.35
    Activations Density 0.007%

    No Known Activations