© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3240
    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
     poches
    -0.58
    TagName
    -0.55
     Océ
    -0.54
     Dodson
    -0.53
    CDATA
    -0.52
    方が
    -0.52
    方を
    -0.51
    zow
    -0.51
     uğ
    -0.51
    方に
    -0.51
    POSITIVE LOGITS
     defaultstate
    0.81
    الدراسه
    0.73
    oredCriteria
    0.68
    AddTagHelper
    0.67
    windowFixed
    0.67
     BoxFit
    0.66
    Билгалдахарш
    0.63
     يتيمه
    0.61
    Hentet
    0.59
    Extinguishing
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.