© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 794
    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
     &___
    -0.53
    galus
    -0.48
    tvguidetime
    -0.45
     tartalomajánló
    -0.45
     etc
    -0.43
    nologi
    -0.43
     hemma
    -0.43
    gecko
    -0.43
    спорта
    -0.41
    igshid
    -0.41
    POSITIVE LOGITS
    Vidite
    0.69
    InjectAttribute
    0.61
     kasarigan
    0.59
    ImageContext
    0.58
    Geplaatst
    0.58
     ménages
    0.58
     Whigs
    0.56
    yntaxException
    0.55
     Wirt
    0.55
     unknownFields
    0.54
    Activations Density 0.055%

    No Known Activations