© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 224
    Prev
    Next
    INDEX
    Explanations

    Percentages

    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
     have
    -0.71
     demonstrate
    -0.61
     possess
    -0.59
     ModelExpression
    -0.54
     require
    -0.52
     HAVE
    -0.52
     liggen
    -0.51
     besitzen
    -0.51
     illustrate
    -0.50
    ecute
    -0.50
    POSITIVE LOGITS
    IntoConstraints
    0.77
     of
    0.66
    transQ
    0.61
     GenerationType
    0.54
     disambiguazione
    0.53
     okuyayım
    0.53
    DrawerToggle
    0.53
    webElementXpaths
    0.51
    rungsseite
    0.50
     scanned
    0.50
    Activations Density 0.007%

    No Known Activations