© 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. 5-CLT-HP
    7. 5437
    Prev
    Next
    INDEX
    Explanations

    as

    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
     the
    -0.82
    :
    -0.66
     Yunnan
    -0.61
     Chopin
    -0.60
     nightmares
    -0.60
     Nirvana
    -0.60
     UCLA
    -0.59
     Dijon
    -0.58
     Archangel
    -0.58
     Sinai
    -0.58
    POSITIVE LOGITS
     InputDecoration
    0.71
     betweenstory
    0.54
    Personensuche
    0.54
     المعيارى
    0.52
    AddTagHelper
    0.49
    TemporalType
    0.49
    ThroughAttribute
    0.48
     Paglinawan
    0.47
     HasFactory
    0.46
    extAlignment
    0.46
    Activations Density 0.002%

    No Known Activations