© 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. 4949
    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
    MockMvc
    -0.47
    การณ์
    -0.44
    örd
    -0.43
    BeanFactory
    -0.41
    ableView
    -0.41
    <eos>
    -0.41
    참고
    -0.40
     Epid
    -0.39
     conda
    -0.38
    ╯
    -0.38
    POSITIVE LOGITS
    :✨
    0.77
     disambiguazione
    0.76
    SourceChecksum
    0.72
    /**
    0.71
     beginnetje
    0.67
     kasarigan
    0.66
     autorytatywna
    0.62
     насељу
    0.61
    Tikang
    0.60
     kaarangay
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.