© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    ISBN and publishing information

    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
     NSCoder
    -0.95
    \{\\
    -0.90
    ContentAlignment
    -0.83
     AssemblyVersion
    -0.83
     '\\;'
    -0.81
    ImageContext
    -0.81
     consultato
    -0.80
    DeleteBehavior
    -0.79
     MainAxisSize
    -0.77
     StatefulWidget
    -0.77
    POSITIVE LOGITS
     pol
    0.39
     socio
    0.38
    URED
    0.38
    ,
    0.37
     lúc
    0.36
     ouro
    0.36
    вто
    0.36
     пом
    0.35
     denn
    0.34
     cober
    0.34
    Activations Density 0.003%

    No Known Activations