© 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. 20-CLT-HP
    7. 73326
    Prev
    Next
    INDEX
    Explanations

    written language

    np_max-act-logits · 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
     propOrder
    -0.75
    cektir
    -0.73
    addCriterion
    -0.71
    PageModule
    -0.71
    ftagPool
    -0.69
    prechpartner
    -0.67
    vician
    -0.66
    cephala
    -0.66
     Meksiku
    -0.65
    :✨
    -0.65
    POSITIVE LOGITS
     alone
    0.56
    ,
    0.52
     alene
    0.44
     تضيفلها
    0.40
     lone
    0.39
     FAR
    0.38
     solo
    0.38
    less
    0.37
     herre
    0.36
     bere
    0.36
    Activations Density 0.014%

    No Known Activations