© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73351
    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
    StoryboardSegue
    -0.89
     الحره
    -0.89
    tvguidetime
    -0.87
    yntaxException
    -0.83
    parsedMessage
    -0.76
    RegressionTest
    -0.75
     typelib
    -0.75
     كومونز
    -0.72
    SequentialGroup
    -0.72
    tagHelperRunner
    -0.71
    POSITIVE LOGITS
     two
    0.63
     multiple
    0.52
     
    0.51
     Roy
    0.49
     Two
    0.46
     second
    0.45
     back
    0.44
    erva
    0.41
     Back
    0.41
     deux
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.