© 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. 11325
    Prev
    Next
    INDEX
    Explanations

    Savannah, Georgia

    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
    ives
    -0.65
     Preview
    -0.62
    qua
    -0.56
     PREVIEW
    -0.53
     preview
    -0.52
    InView
    -0.47
     maș
    -0.46
     complètes
    -0.44
     tén
    -0.43
     épreuves
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.92
    tagHelperRunner
    0.85
    richTextPanel
    0.76
    JsonHelper
    0.74
    CPtr
    0.73
     mergeFrom
    0.71
     Biôgrafia
    0.69
    MemoryWarning
    0.69
    msgTypes
    0.68
    Personensuche
    0.67
    Activations Density 0.024%

    No Known Activations