© 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. 9254
    Prev
    Next
    INDEX
    Explanations

    covalent

    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
     covalent
    -0.81
     تضيفلها
    -0.73
    gers
    -0.71
    WriteTagHelper
    -0.69
    webElement
    -0.66
    styleType
    -0.62
     المعيارى
    -0.61
     CreateTagHelper
    -0.60
    ArrowToggle
    -0.59
    Handel
    -0.57
    POSITIVE LOGITS
    Tembelea
    0.63
    NameInMap
    0.62
    CreateModel
    0.49
    alba
    0.45
     omission
    0.44
     poise
    0.44
     inter
    0.43
     setId
    0.43
    Economia
    0.43
     Fo
    0.43
    Activations Density 0.003%

    No Known Activations