© 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. 4556
    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
    UnsafeEnabled
    -0.80
    webElementXpaths
    -0.65
     Nacionales
    -0.63
     EconPapers
    -0.59
    InvalidProtocol
    -0.57
     imageNamed
    -0.55
    BeginInit
    -0.54
    ↹
    -0.53
     الحره
    -0.53
    EndInit
    -0.51
    POSITIVE LOGITS
    ReusableCell
    0.64
     soi
    0.61
     ModelExpression
    0.55
     Oft
    0.54
     often
    0.51
    ordano
    0.50
    таратура
    0.50
    allu
    0.50
    ibos
    0.49
     vell
    0.49
    Activations Density 0.000%

    No Known Activations