© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1989
    Prev
    Next
    INDEX
    Explanations

    to

    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
     remplacé
    -0.68
    出版年
    -0.61
    MigrationBuilder
    -0.60
     écout
    -0.58
     étoit
    -0.57
    saraba
    -0.56
     religieuses
    -0.53
     debout
    -0.52
     nød
    -0.52
     pohled
    -0.52
    POSITIVE LOGITS
     justify
    0.71
     argue
    0.69
     describe
    0.66
     decry
    0.65
     rail
    0.64
     насељу
    0.63
     demand
    0.61
    ViewImports
    0.60
     attack
    0.59
    describe
    0.59
    Activations Density 0.005%

    No Known Activations