© 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. 91939
    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
    Personendaten
    -0.86
     JpaRepository
    -0.78
    +#+#
    -0.76
    TypedDataSet
    -0.74
    "]}
    -0.69
    Hochspringen
    -0.67
    rungsseite
    -0.66
     BoxDecoration
    -0.66
    _
    -0.64
    DoubleQuotes
    -0.62
    POSITIVE LOGITS
    campista
    0.42
    CodeAttribute
    0.42
    hdysval
    0.41
     unwritten
    0.40
     onItemClick
    0.40
     kvä
    0.39
     Mockito
    0.38
    mouseleave
    0.38
    chad
    0.38
    neum
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.