© 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. 91724
    Prev
    Next
    INDEX
    Explanations

    Time

    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
     AssemblyProduct
    -0.65
     ready
    -0.59
    <bos>
    -0.58
    $_['
    -0.52
     hir
    -0.47
    ready
    -0.46
    श्यक
    -0.46
    itive
    -0.45
    Hir
    -0.43
    cont
    -0.43
    POSITIVE LOGITS
    хьтан
    0.65
     Gump
    0.64
    tagHelperRunner
    0.62
    出版年
    0.60
    URLException
    0.57
    الإنجليزية
    0.56
    Vidite
    0.56
     către
    0.56
     OFDb
    0.55
     viewType
    0.54
    Activations Density 0.030%

    No Known Activations