© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9814
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    beek
    -0.51
    WaitGroup
    -0.50
    CompleteListener
    -0.46
     
    -0.45
     hard
    -0.45
     modern
    -0.44
     ring
    -0.44
     her
    -0.44
     by
    -0.43
     best
    -0.42
    POSITIVE LOGITS
    +#+#
    1.14
     Roskov
    0.94
     stanovnika
    0.79
     ModelExpression
    0.79
     kasarigan
    0.76
     Witkin
    0.75
     Paglinawan
    0.74
    Chham
    0.73
    chism
    0.72
     photolibrary
    0.72
    Activations Density 1.970%

    No Known Activations