© 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. 15941
    Prev
    Next
    INDEX
    Explanations

    Russia/Soviet Union related texts

    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
     habet
    -0.45
     greu
    -0.41
     cardin
    -0.40
    "
    -0.40
     holotype
    -0.40
     latina
    -0.39
     kirke
    -0.39
     Coleridge
    -0.37
     mauri
    -0.37
    исленность
    -0.37
    POSITIVE LOGITS
    BufferException
    0.75
     AssemblyTitle
    0.75
    __':
    0.73
     MessageBoxIcon
    0.71
    NUMX
    0.69
    IsContent
    0.68
    UnknownFieldSet
    0.68
     Stop
    0.66
    emption
    0.65
    modelBuilder
    0.65
    Activations Density 0.010%

    No Known Activations