© 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. 77861
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    ftagPool
    -0.64
    ArrowToggle
    -0.58
    AutoScaleMode
    -0.58
     kaarangay
    -0.57
    JspWriter
    -0.56
    transQ
    -0.52
    ThroughAttribute
    -0.52
    Życiorys
    -0.51
     Soler
    -0.50
     Meksiku
    -0.49
    POSITIVE LOGITS
    }{*}{
    0.54
    producción
    0.54
     nahilalakip
    0.53
    ülé
    0.52
     Model
    0.52
     Field
    0.50
     Lab
    0.50
     field
    0.48
    getField
    0.48
    rophoresis
    0.47
    Activations Density 0.000%

    No Known Activations