© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74809
    Prev
    Next
    INDEX
    Explanations

    computer code/technical language

    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
    stdc
    -0.72
    TypedDataSet
    -0.65
     StatelessWidget
    -0.63
    utilisons
    -0.59
    jstor
    -0.57
    WithIOException
    -0.57
    ffindor
    -0.56
    Band
    -0.54
     AspNetCore
    -0.53
    bands
    -0.52
    POSITIVE LOGITS
     '\\;'
    0.69
     CreateTagHelper
    0.57
    HasForeignKey
    0.52
    ̈́
    0.50
     Chamberlain
    0.48
    ostante
    0.46
    XtraReports
    0.45
     Raff
    0.45
    ExtendWith
    0.44
    StringLen
    0.42
    Activations Density 0.000%

    No Known Activations