© 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. 1-CLT-HP
    7. 10190
    Prev
    Next
    INDEX
    Explanations

    esters

    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
    sizeCache
    -0.73
    RegistryLite
    -0.72
    expandindo
    -0.65
    ///</
    -0.64
    principalTable
    -0.63
    SpringRunner
    -0.63
    XmlAccessType
    -0.62
    ContentLoaded
    -0.61
    setVerticalGroup
    -0.58
    jooq
    -0.58
    POSITIVE LOGITS
    \{\\
    0.50
    براير
    0.48
    例文帳に追加
    0.44
    BindView
    0.44
     *);
    0.43
    <?>>
    0.41
    vantaged
    0.41
     Maat
    0.40
    zkod
    0.40
     voie
    0.40
    Activations Density 0.027%

    No Known Activations