© 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. 0-CLT-HP
    7. 42924
    Prev
    Next
    INDEX
    Explanations

    held

    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
     held
    -2.05
     Held
    -1.90
    Held
    -1.84
    held
    -1.83
     HELD
    -1.56
    hold
    -1.43
    Hold
    -1.22
     Holds
    -1.17
     holds
    -1.16
     hold
    -1.16
    POSITIVE LOGITS
     down
    0.80
     up
    0.79
     for
    0.65
     onto
    0.63
     back
    0.63
     out
    0.60
     on
    0.59
     an
    0.57
     all
    0.55
     a
    0.54
    Activations Density 0.018%

    No Known Activations