© 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. 0-CLT-HP
    7. 95542
    Prev
    Next
    INDEX
    Explanations

    formal language

    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
    Negative Logits
    ILogger
    -0.54
     UserId
    -0.48
     Epidemio
    -0.47
     UIImage
    -0.47
     GPS
    -0.45
    tvguidetime
    -0.44
     fabricants
    -0.44
    AccountId
    -0.43
     BufferedImage
    -0.42
     ILogger
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.77
     كومونز
    0.74
    DockStyle
    0.68
     SEDS
    0.67
    MigrationBuilder
    0.66
    QMetaType
    0.65
    Personendaten
    0.63
    ScopeManager
    0.62
    ToBounds
    0.62
     препратки
    0.62
    Activations Density 0.027%

    No Known Activations