© 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. 5-CLT-HP
    7. 93831
    Prev
    Next
    INDEX
    Explanations

    code-related

    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
     Roskov
    -0.82
     للمعارف
    -0.71
     AttributeSet
    -0.69
     disambiguazione
    -0.67
    StoryboardSegue
    -0.62
    ensement
    -0.60
    XmlAccessorType
    -0.60
     AssemblyCompany
    -0.59
    GeneratedValue
    -0.59
    født
    -0.57
    POSITIVE LOGITS
     re
    0.47
    Calais
    0.47
     Attached
    0.46
    fores
    0.45
    :
    0.44
    Attached
    0.44
    ancourt
    0.43
    anthrene
    0.43
    czuk
    0.43
     sharing
    0.43
    Activations Density 0.012%

    No Known Activations