© 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. 77148
    Prev
    Next
    INDEX
    Explanations

    Months

    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
     AssemblyCulture
    -1.01
    RegistryLite
    -0.77
     pinulongan
    -0.76
    mybatisplus
    -0.73
    InSection
    -0.72
     CreateTagHelper
    -0.71
    DebuggerNonUser
    -0.69
    yntaxException
    -0.68
    unknownFields
    -0.68
    httphttps
    -0.68
    POSITIVE LOGITS
     one
    0.72
     One
    0.72
     second
    0.63
     two
    0.59
    One
    0.58
     Second
    0.57
     Two
    0.57
    一
    0.56
    dotto
    0.55
     satu
    0.54
    Activations Density 0.003%

    No Known Activations