© 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. 4-CLT-HP
    7. 627
    Prev
    Next
    INDEX
    Explanations

    who

    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
     kasarigan
    -0.98
    OGND
    -0.96
     الحره
    -0.93
    MessageOf
    -0.90
    contentLoaded
    -0.89
    WebElementEntity
    -0.89
    ThroughAttribute
    -0.87
    RectangleBorder
    -0.85
     EconPapers
    -0.85
     surla
    -0.84
    POSITIVE LOGITS
     are
    0.94
     have
    0.91
     were
    0.85
    ,
    0.73
     say
    0.68
     find
    0.62
     feel
    0.58
     complain
    0.56
     continue
    0.55
     worry
    0.54
    Activations Density 0.001%

    No Known Activations