© 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. 93750
    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
    DockStyle
    -0.71
     препратки
    -0.69
    MigrationBuilder
    -0.69
    رشف
    -0.68
    ísimas
    -0.65
    kháu
    -0.64
    OptionsMenu
    -0.64
    ]--;
    -0.60
    Демографія
    -0.59
     disambiguazione
    -0.59
    POSITIVE LOGITS
     working
    0.51
    arial
    0.46
    Viper
    0.45
     hating
    0.41
     Working
    0.41
     great
    0.41
     saying
    0.40
     مرور
    0.40
    ar
    0.40
    orious
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.