© 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. 20-CLT-HP
    7. 77458
    Prev
    Next
    INDEX
    Explanations

    attention

    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
    rungsseite
    -0.93
    complexContent
    -0.84
     متعلقه
    -0.81
    SourceChecksum
    -0.70
    ագրություններ
    -0.69
     intptr
    -0.68
    IntoConstraints
    -0.67
    Зноскі
    -0.66
     للمعارف
    -0.65
    contentLoaded
    -0.60
    POSITIVE LOGITS
     attention
    0.90
     undue
    0.56
     added
    0.55
     attendance
    0.54
     atten
    0.53
     special
    0.53
     regularity
    0.51
     greater
    0.51
     aten
    0.51
     ATTENTION
    0.50
    Activations Density 0.007%

    No Known Activations