© 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. 3435
    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
    getDescriptor
    -0.61
    ManagedBean
    -0.60
     god
    -0.59
    >*/
    -0.57
     religion
    -0.57
    .\\
    -0.56
    boldmath
    -0.56
    .。
    -0.55
     material
    -0.54
    hlungen
    -0.54
    POSITIVE LOGITS
     blessés
    0.60
     colorés
    0.58
     déchir
    0.58
     dignité
    0.57
     lumières
    0.57
     blessures
    0.57
     leçon
    0.56
     skydd
    0.56
     traités
    0.55
     démocr
    0.54
    Activations Density 0.000%

    No Known Activations