© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    Song

    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
     Song
    -1.11
    Song
    -0.92
     SONG
    -0.68
     song
    -0.62
    ypes
    -0.55
    SONG
    -0.55
     SBS
    -0.55
    참고
    -0.54
    łop
    -0.54
     birth
    -0.53
    POSITIVE LOGITS
    XmlAccessType
    0.77
     AssemblyCulture
    0.62
     wireType
    0.61
     transfieras
    0.59
    #+#
    0.59
    Демографія
    0.54
    oredCriteria
    0.50
    MigrationBuilder
    0.50
    anément
    0.49
    zzleHttp
    0.48
    Activations Density 0.028%

    No Known Activations