© 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. 0-CLT-HP
    7. 97111
    Prev
    Next
    INDEX
    Explanations

    realize

    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
     realize
    -1.66
     realized
    -1.66
     realised
    -1.61
     realise
    -1.60
     realizes
    -1.52
     realises
    -1.50
     realizing
    -1.45
     realising
    -1.38
     realisation
    -1.22
     realization
    -1.20
    POSITIVE LOGITS
     parseFrom
    0.57
    DrawerToggle
    0.57
     rumble
    0.53
    ี้ยง
    0.53
    principalColumn
    0.52
    PathVariable
    0.48
     postIndex
    0.48
     Parke
    0.47
     incidentally
    0.47
     staked
    0.47
    Activations Density 0.273%

    No Known Activations