© 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. 76405
    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
    LEncoder
    -0.68
    WriteTagHelper
    -0.64
     Вікі
    -0.64
     transfieras
    -0.63
    帖最后由
    -0.62
     competency
    -0.61
    bewerken
    -0.60
    AddTagHelper
    -0.60
     跳转至
    -0.60
     lenker
    -0.60
    POSITIVE LOGITS
    RunWith
    0.49
     depic
    0.42
    atief
    0.36
    Архівовано
    0.35
    PROT
    0.33
    aA
    0.32
    CastException
    0.32
     siste
    0.31
    ̀n
    0.31
    Ric
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.