© 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. 1-CLT-HP
    7. 9915
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    principalTable
    -0.81
    ISupport
    -0.75
     للمعارف
    -0.71
     فريبيس
    -0.59
     sī
    -0.57
     发表于
    -0.56
     pinulongan
    -0.56
    cokinetic
    -0.52
     nakalista
    -0.52
    はじめに
    -0.51
    POSITIVE LOGITS
     démocr
    0.58
    pepe
    0.54
    endi
    0.53
     initComponents
    0.52
     élas
    0.52
    wendi
    0.51
     économiques
    0.51
     sauvages
    0.50
    wind
    0.50
    w
    0.49
    Activations Density 0.016%

    No Known Activations