© 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. 20-CLT-HP
    7. 76452
    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
     EconPapers
    -0.71
     resourceCulture
    -0.66
    RenderAtEndOf
    -0.57
     occupe
    -0.49
     triko
    -0.48
    PickerController
    -0.46
     fallait
    -0.46
     defaultstate
    -0.45
    اهش
    -0.45
    Ev
    -0.45
    POSITIVE LOGITS
    TagMode
    0.68
     ddelweddau
    0.62
    OGND
    0.58
     mAdapter
    0.56
     estekak
    0.55
    =$?
    0.54
     typelib
    0.54
     AssemblyTitle
    0.54
    IsMutable
    0.53
    AdapterView
    0.52
    Activations Density 0.000%

    No Known Activations