© 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. 4-CLT-HP
    7. 37
    Prev
    Next
    INDEX
    Explanations

    PropertyGroup

    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
    abetes
    -0.63
     дописавши
    -0.60
     Data
    -0.57
     Measuring
    -0.57
    ording
    -0.57
     data
    -0.57
     measuring
    -0.55
    DockStyle
    -0.55
    __*/
    -0.55
     measurement
    -0.54
    POSITIVE LOGITS
     تضيفلها
    0.60
     føl
    0.54
    featureID
    0.53
    principal
    0.46
     oprot
    0.44
     brancas
    0.44
     impea
    0.44
    viewDidLoad
    0.44
    ChromeDriver
    0.44
     pardoned
    0.43
    Activations Density 0.001%

    No Known Activations