© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15881
    Prev
    Next
    INDEX
    Explanations

    infections

    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
    DockStyle
    -0.66
    skosten
    -0.59
    cassert
    -0.54
    صیل
    -0.52
    HasIndex
    -0.51
     betweenstory
    -0.50
    FormTagHelper
    -0.49
    __(/*!
    -0.49
    ulets
    -0.49
     boisson
    -0.49
    POSITIVE LOGITS
    QMetaType
    0.58
    aspectj
    0.55
    StoryboardSegue
    0.54
    -
    0.50
    stage
    0.50
    AccessorTable
    0.50
    UnknownFields
    0.49
     Spo
    0.49
    Spo
    0.47
     succession
    0.47
    Activations Density 0.136%

    No Known Activations