© 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. 4-CLT-HP
    7. 2322
    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
    SharedDtor
    -0.56
    setVerticalGroup
    -0.55
    UIControlState
    -0.54
    ScopeManager
    -0.54
    󠁢
    -0.51
     `"
    -0.49
    AccessFile
    -0.49
    createCanvas
    -0.49
    «<
    -0.49
    ConstraintMaker
    -0.48
    POSITIVE LOGITS
    Rüyada
    0.67
    Vidite
    0.67
     estimés
    0.64
     hoeft
    0.52
    дравствуйте
    0.52
    exels
    0.52
    XmlIgnore
    0.52
    mschrijving
    0.51
     škoda
    0.50
    Здравствуйте
    0.49
    Activations Density 0.002%

    No Known Activations