© 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. 4319
    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
    classnames
    -0.64
    CppCodeGen
    -0.52
    keyCode
    -0.50
     SET
    -0.48
    iglio
    -0.46
     Nexus
    -0.46
    nail
    -0.45
    melho
    -0.43
     Stratton
    -0.42
     HTC
    -0.42
    POSITIVE LOGITS
    Personensuche
    0.62
    MessageOf
    0.59
     архивлан
    0.54
     ComVisible
    0.51
     unknownFields
    0.51
     betweenstory
    0.51
    geist
    0.49
     reclamo
    0.49
    "](
    0.48
    SourceChecksum
    0.48
    Activations Density 0.000%

    No Known Activations