© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78213
    Prev
    Next
    INDEX
    Explanations

    incoherent text

    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
    Negative Logits
    Manbalar
    -0.57
     estekak
    -0.57
    GetMapping
    -0.57
     groupName
    -0.55
    Spoljašnje
    -0.55
    зулта
    -0.54
    Personensuche
    -0.53
     '\\;'
    -0.50
    styleable
    -0.50
    IUrlHelper
    -0.49
    POSITIVE LOGITS
    casio
    0.60
     sèche
    0.60
    TableAdapter
    0.60
    nodoc
    0.57
    Run
    0.55
    twimg
    0.54
    run
    0.53
     Run
    0.52
    }]
    0.51
    BagConstraints
    0.50
    Activations Density 0.000%

    No Known Activations