© 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. 92271
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    drücken
    -0.63
    [][
    -0.48
    før
    -0.46
    ckså
    -0.45
    AlreadyExists
    -0.45
     stället
    -0.45
     yürü
    -0.44
     ''),
    -0.44
    ']/
    -0.43
     föruts
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.93
    parsedMessage
    0.87
    ագրություններ
    0.83
     ExecuteAsync
    0.80
    Tembelea
    0.79
    PreferredItem
    0.76
     Normdatei
    0.75
     ***!
    0.75
    IndentedString
    0.74
    ImageContext
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.