© 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. 4-CLT-HP
    7. 1750
    Prev
    Next
    INDEX
    Explanations

    jurisdictions

    np_max-act · gemini-2.0-flash
    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
    TRAILING
    -0.45
     propOrder
    -0.45
    ly
    -0.43
    +#+#
    -0.43
    ichar
    -0.41
     OMITBAD
    -0.41
    American
    -0.40
    .
    -0.39
    ering
    -0.38
    TagHelper
    -0.37
    POSITIVE LOGITS
     of
    0.90
    帖最后由
    0.75
     urbanas
    0.67
     fermés
    0.65
     της
    0.65
     gouttes
    0.63
     boî
    0.62
     béné
    0.60
     rayures
    0.60
     Provinsi
    0.60
    Activations Density 0.091%

    No Known Activations