© 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. 20-CLT-HP
    7. 72406
    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
    SequentialGroup
    -0.75
     AssemblyCulture
    -0.72
    SourceChecksum
    -0.70
    🗳
    -0.68
    WriteTagHelper
    -0.65
    NUMX
    -0.63
     Tivoli
    -0.63
    addCriterion
    -0.63
     Réponses
    -0.63
    StructEnd
    -0.63
    POSITIVE LOGITS
    RectangleBorder
    0.39
     Wikimédia
    0.39
    ágos
    0.38
    maus
    0.36
     Cin
    0.35
    Five
    0.34
    uat
    0.34
    Hint
    0.34
     Fünf
    0.34
     parede
    0.33
    Activations Density 0.004%

    No Known Activations