© 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. 97278
    Prev
    Next
    INDEX
    Explanations

    etc

    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
     etc
    -1.14
    etc
    -0.82
    ay
    -0.81
     Etc
    -0.74
     usw
    -0.70
    Etc
    -0.64
     등
    -0.63
    J
    -0.61
     cannot
    -0.60
    などなど
    -0.58
    POSITIVE LOGITS
     disambiguazione
    0.93
     AssemblyCompany
    0.88
     myſelf
    0.82
    writeFieldEnd
    0.79
     estekak
    0.77
     itſelf
    0.77
    GraphicsUnit
    0.75
    EDEFAULT
    0.73
     فريبيس
    0.69
     متعلقه
    0.68
    Activations Density 1.625%

    No Known Activations