© 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. 13939
    Prev
    Next
    INDEX
    Explanations

    coli

    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
    ✨:
    -0.65
    
    -0.60
    InputTagHelper
    -0.56
     aureus
    -0.56
    astify
    -0.54
    rawDesc
    -0.54
    findpost
    -0.54
    stateProvider
    -0.54
     CreateTagHelper
    -0.54
    fxml
    -0.54
    POSITIVE LOGITS
    Pyx
    0.61
    ⓧ
    0.56
    sin
    0.50
    CreateTable
    0.48
    Referenced
    0.48
     Lulu
    0.47
    azer
    0.46
    scl
    0.46
     inactivity
    0.46
    γραφία
    0.45
    Activations Density 0.022%

    No Known Activations