© 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. 92182
    Prev
    Next
    INDEX
    Explanations

    People (ending in -ers/-ors)

    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
    mobileqq
    -0.58
    kuuta
    -0.57
    SharedDtor
    -0.52
    ELIA
    -0.52
     misfortunes
    -0.51
    COMING
    -0.50
    (@"%@",
    -0.50
     vices
    -0.50
    erequisites
    -0.50
     spellings
    -0.50
    POSITIVE LOGITS
    ArrowToggle
    0.87
     and
    0.69
     recommend
    0.58
     StatefulWidget
    0.56
    Diweddarwch
    0.51
     agree
    0.50
     GetEnumerator
    0.49
     love
    0.49
     recommande
    0.48
     believe
    0.48
    Activations Density 0.002%

    No Known Activations