© 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. 75768
    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
    الإنجليزية
    -0.55
     peggio
    -0.54
    AYER
    -0.50
     MERCHANTABILITY
    -0.50
     Epid
    -0.49
     AQU
    -0.49
    Erreferentziak
    -0.48
     internes
    -0.47
    কার
    -0.47
    aufen
    -0.47
    POSITIVE LOGITS
    awtextra
    0.64
    UrlResolution
    0.56
     linkovi
    0.53
    stonia
    0.52
    __':
    0.52
    SharedCtor
    0.51
    JspWriter
    0.50
    GEBURTSDATUM
    0.50
     jScrollPane
    0.50
     Савезне
    0.50
    Activations Density 0.000%

    No Known Activations