© 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. 0-CLT-HP
    7. 42268
    Prev
    Next
    INDEX
    Explanations

    disruption

    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
     otomatig
    -0.82
    GEBURTSDATUM
    -0.78
    diversity
    -0.71
    цездатний
    -0.70
    AddTagHelper
    -0.69
    LookAnd
    -0.68
    CloseOperation
    -0.68
    nione
    -0.67
    XmlType
    -0.66
    SourceChecksum
    -0.66
    POSITIVE LOGITS
    ity
    0.58
    ally
    0.50
    sok
    0.48
    ary
    0.48
    criminator
    0.47
    存于互联网档案馆
    0.47
     commenter
    0.45
     intérprete
    0.44
    saurus
    0.43
     itſelf
    0.42
    Activations Density 0.050%

    No Known Activations