© 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. 0-CLT-HP
    7. 93712
    Prev
    Next
    INDEX
    Explanations

    carried

    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
     carried
    -2.72
    carried
    -2.50
     Carrying
    -2.23
     Carried
    -2.22
     carrying
    -2.17
    Carrying
    -2.17
    carrying
    -2.13
     CARRY
    -1.48
    carry
    -1.42
     carry
    -1.41
    POSITIVE LOGITS
     out
    0.54
     a
    0.51
     up
    0.46
     forth
    0.45
     away
    0.44
     an
    0.43
    assigns
    0.43
     host
    0.43
     succession
    0.43
     gram
    0.42
    Activations Density 0.182%

    No Known Activations