© 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. 5-CLT-HP
    7. 91384
    Prev
    Next
    INDEX
    Explanations

    rx

    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
     оригіналу
    -0.52
    حياتها
    -0.47
    SessionFactory
    -0.42
    出版年
    -0.42
     vPvB
    -0.42
    runge
    -0.41
     sheaves
    -0.41
     rip
    -0.40
    jsonPath
    -0.40
    ModelAdmin
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.75
     propOrder
    0.67
    SourceChecksum
    0.66
     otomatig
    0.65
     resourceCulture
    0.64
    ])));
    0.64
    )++;
    0.63
    省市镇
    0.62
    ])):
    0.60
     NSCoder
    0.60
    Activations Density 0.003%

    No Known Activations