© 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. 0-CLT-HP
    7. 92943
    Prev
    Next
    INDEX
    Explanations

    hear

    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
     hear
    -3.61
     Hear
    -2.67
    hear
    -2.52
    Hear
    -2.44
     hears
    -2.39
     HEAR
    -2.34
     hearing
    -1.51
     ouvir
    -1.38
    hears
    -1.34
     listen
    -1.28
    POSITIVE LOGITS
     the
    0.82
    IUrlHelper
    0.71
     a
    0.69
    fromnode
    0.61
     this
    0.59
     it
    0.59
     them
    0.52
     their
    0.51
     an
    0.50
     some
    0.49
    Activations Density 0.106%

    No Known Activations