© 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. 5-CLT-HP
    7. 92787
    Prev
    Next
    INDEX
    Explanations

    Ra

    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
     doubtnut
    -0.66
     فريبيس
    -0.56
    endphp
    -0.55
     dégustation
    -0.54
     picioare
    -0.53
     arşivlendi
    -0.52
    ecap
    -0.51
     photolibrary
    -0.51
    haustible
    -0.49
    ImageContext
    -0.48
    POSITIVE LOGITS
     AssemblyTitle
    0.75
     “
    0.70
    ['
    0.66
     "
    0.65
    rawDesc
    0.64
    ’
    0.63
     ‘
    0.60
    
    0.59
    viewDidLoad
    0.59
    ↵↵
    0.59
    Activations Density 0.019%

    No Known Activations