© 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. 76162
    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
    帖最后由
    -0.54
     Loaf
    -0.48
    adona
    -0.48
    digans
    -0.44
     Kli
    -0.43
    UpInside
    -0.43
    esez
    -0.42
     OnTriggerEnter
    -0.42
    Jegyzetek
    -0.41
    GEBURTSDATUM
    -0.41
    POSITIVE LOGITS
    protoimpl
    0.67
     pilot
    0.65
    
    0.60
    IUrlHelper
    0.60
    XMLSchema
    0.56
    > 
    0.53
    st
    0.52
    TestTools
    0.52
    PROTOBUF
    0.52
    actionMode
    0.52
    Activations Density 0.000%

    No Known Activations