© 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. 5-CLT-HP
    7. 97911
    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
     so
    -0.51
    '
    -0.48
     "
    -0.48
    so
    -0.47
    ’
    -0.47
     really
    -0.46
     does
    -0.45
     “
    -0.45
    akyti
    -0.44
     si
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.78
     uſed
    0.76
     المعيارى
    0.73
     myſelf
    0.73
    engertian
    0.71
    ButterKnife
    0.70
     ſhe
    0.68
    DataMember
    0.68
    IntoConstraints
    0.67
    CppMethod
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.