© 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. 93821
    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
     habet
    -0.59
     quæ
    -0.59
     tesoro
    -0.56
     westfalen
    -0.56
    maketitle
    -0.54
     précie
    -0.54
     généraux
    -0.53
     purpoſe
    -0.53
     âme
    -0.52
     vœux
    -0.52
    POSITIVE LOGITS
     виправивши
    0.67
    RegressionTest
    0.66
    expandindo
    0.64
     مرئيه
    0.62
    aarrggbb
    0.61
    WithIOException
    0.59
     createSlice
    0.59
    XmlType
    0.58
    queryInterface
    0.58
    thâu
    0.57
    Activations Density 0.000%

    No Known Activations