© 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. 20-CLT-HP
    7. 72788
    Prev
    Next
    INDEX
    Explanations

    pop

    np_max-act-logits · 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
    WriteLiteral
    -0.75
     initComponents
    -0.70
    DeleteBehavior
    -0.69
     NSCoder
    -0.66
     snippetHide
    -0.61
     Infórmanos
    -0.61
     defStyleAttr
    -0.60
     disambiguazione
    -0.59
    titleMargin
    -0.59
    isContained
    -0.59
    POSITIVE LOGITS
     pop
    0.66
     Pop
    0.66
    pop
    0.64
     POP
    0.56
    Pop
    0.56
    beth
    0.52
     Satellite
    0.50
     v
    0.48
    v
    0.46
    POP
    0.45
    Activations Density 0.003%

    No Known Activations