© 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. 0-CLT-HP
    7. 1466
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ”.
    -0.66
    .”
    -0.66
    ).
    -0.60
    ".
    -0.60
    ").
    -0.57
    ".
    -0.57
     she
    -0.56
     well
    -0.56
    ."
    -0.55
    ).
    -0.55
    POSITIVE LOGITS
     The
    1.09
    ↵↵
    1.00
     This
    0.99
     It
    0.95
     There
    0.93
    ↵
    0.92
     But
    0.90
     Some
    0.89
     Those
    0.88
     These
    0.86
    Activations Density 0.222%

    No Known Activations