© 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. 97375
    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
     <<<<<<<<<<<<<<
    -0.71
    msgTypes
    -0.66
     سكانية
    -0.59
     FetchType
    -0.59
     يتيمه
    -0.59
    afficheront
    -0.57
     détruire
    -0.56
     Paglinawan
    -0.56
    sedown
    -0.56
     appId
    -0.55
    POSITIVE LOGITS
    AccessorTable
    0.73
     oprot
    0.56
     createState
    0.53
    GraphicsUnit
    0.52
     CreateTagHelper
    0.52
    
    0.52
    SPATH
    0.51
    antMatchers
    0.51
    __":
    0.50
     betweenstory
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.