© 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. 20-CLT-HP
    7. 73531
    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
     للاسماء
    -0.76
    SuppressMessage
    -0.69
    AddTagHelper
    -0.68
    #+#
    -0.67
    NameInMap
    -0.66
    HasAnnotation
    -0.65
    +#+
    -0.64
    PhD
    -0.63
    PhysRevD
    -0.63
    曖昧さ回避
    -0.63
    POSITIVE LOGITS
     group
    0.64
    NOPQRST
    0.57
     насељу
    0.50
     Group
    0.49
     GROUP
    0.48
     staff
    0.47
     groupe
    0.46
    group
    0.44
    ული
    0.43
    सन्दर्भ
    0.42
    Activations Density 0.000%

    No Known Activations