© 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. 72703
    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
    MemoryWarning
    -0.82
    findpost
    -0.69
    SpringRunner
    -0.66
     createState
    -0.65
    ⓧ
    -0.63
    Jeografia
    -0.61
     समीक्षक
    -0.60
    PYX
    -0.60
    msgTypes
    -0.60
    setVerticalGroup
    -0.57
    POSITIVE LOGITS
     consultato
    0.56
     publish
    0.50
    onomía
    0.47
     chirurgie
    0.47
     publié
    0.47
     Publish
    0.47
     PUBLICATION
    0.46
     flèche
    0.45
     ilmo
    0.45
     published
    0.45
    Activations Density 0.004%

    No Known Activations