© 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. 96306
    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
    ustimmung
    -0.48
     vectorielles
    -0.46
    enumi
    -0.45
     AppCompatTheme
    -0.45
     boî
    -0.45
     مشين
    -0.43
     rayures
    -0.41
    €¦
    -0.40
     générations
    -0.39
     étoile
    -0.39
    POSITIVE LOGITS
    новништво
    0.69
     '\\;'
    0.66
    ngdoc
    0.61
     SafeMath
    0.60
     newBuilder
    0.59
     geologists
    0.59
    uxxxx
    0.59
     ProtoMessage
    0.58
    guys
    0.57
    iramente
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.