© 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. 5-CLT-HP
    7. 4959
    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
     quæ
    -0.60
    asgi
    -0.60
    onsored
    -0.59
     ejus
    -0.59
     ſch
    -0.58
     sherds
    -0.57
     Reſ
    -0.56
     iſt
    -0.55
     houſe
    -0.55
     ſei
    -0.54
    POSITIVE LOGITS
     didnt
    0.80
     didn
    0.80
     did
    0.78
     I
    0.76
     wasnt
    0.76
     definitely
    0.73
     he
    0.73
    ,
    0.72
     i
    0.72
     wasn
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.