© 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. 96589
    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
     Offense
    -0.45
     affaire
    -0.43
    过后
    -0.43
    τω
    -0.42
     htons
    -0.41
     capace
    -0.41
     angeles
    -0.41
     Lade
    -0.41
     Napole
    -0.40
    ruit
    -0.39
    POSITIVE LOGITS
     nahilalakip
    0.89
     estekak
    0.85
    writeFieldEnd
    0.85
    oa̍t
    0.84
    EDEFAULT
    0.82
    ">//
    0.81
     Référence
    0.80
    InvalidProtocol
    0.79
     дописавши
    0.79
    出版年
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.