© 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. 1-CLT-HP
    7. 13628
    Prev
    Next
    INDEX
    Explanations

    ba

    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
    ba
    -1.13
    bha
    -0.86
    BA
    -0.70
     ba
    -0.69
    Ba
    -0.65
     Ba
    -0.61
    spesies
    -0.59
     gärna
    -0.56
    joba
    -0.54
     sebou
    -0.54
    POSITIVE LOGITS
     للمعارف
    0.61
     تضيفلها
    0.61
    sizeCache
    0.61
    CodedInputStream
    0.57
    VIAF
    0.57
     Brust
    0.53
     protoimpl
    0.52
     BIBSYS
    0.52
     lượt
    0.51
    ńst
    0.51
    Activations Density 0.046%

    No Known Activations