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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1628
    Prev
    Next
    INDEX
    Explanations

    are and parentheses

    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
     lắm
    -0.51
    GEBURTSDATUM
    -0.51
    SourceChecksum
    -0.50
    Tam
    -0.49
    
    -0.47
    expandindo
    -0.46
     EconPapers
    -0.46
    ifflin
    -0.45
    addPreferredGap
    -0.45
    aas
    -0.45
    POSITIVE LOGITS
     pageContext
    0.67
    phane
    0.57
    Rüyada
    0.52
    ništvo
    0.50
    DebuggerNonUser
    0.49
    ukkah
    0.49
    greenrobot
    0.49
    diğinde
    0.49
     MainAxisSize
    0.48
    Према
    0.48
    Activations Density 0.020%

    No Known Activations