© 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. 5-CLT-HP
    7. 5893
    Prev
    Next
    INDEX
    Explanations

    this

    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
    PYX
    -0.69
     StringTokenizer
    -0.58
    migrationBuilder
    -0.58
     يتيمه
    -0.56
    ỡng
    -0.53
    oznam
    -0.52
    OCCURRED
    -0.50
     Referential
    -0.50
    jeo
    -0.50
    참고
    -0.48
    POSITIVE LOGITS
    devServer
    0.51
     Welsh
    0.49
    inema
    0.49
     revenu
    0.48
     Saxons
    0.48
    titleMargin
    0.48
    amom
    0.47
    FactoryBean
    0.47
    pædia
    0.47
    &=&\
    0.47
    Activations Density 0.046%

    No Known Activations