© 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. 76828
    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
    ValueStyle
    -0.94
    SequentialGroup
    -0.91
    цездатний
    -0.90
    tagHelperRunner
    -0.86
    SourceChecksum
    -0.85
     '\\;'
    -0.82
    uxxxx
    -0.82
    GeneratedValue
    -0.81
     ostavi
    -0.81
     المعيارى
    -0.80
    POSITIVE LOGITS
     six
    0.83
     
    0.60
     SIX
    0.48
     sechs
    0.48
     Six
    0.44
     two
    0.43
    六
    0.43
    six
    0.42
     three
    0.41
     seis
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.