© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73435
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act-logits · 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
    enumi
    -0.61
    wards
    -0.57
    rxjs
    -0.54
    iners
    -0.51
    WARDS
    -0.51
    estimators
    -0.50
     Italijani
    -0.50
    reuung
    -0.49
    +#+
    -0.48
    WISE
    -0.48
    POSITIVE LOGITS
    principalTable
    0.56
     виправивши
    0.52
    RegistryLite
    0.52
    fromnode
    0.50
     vérit
    0.49
     aveug
    0.49
     mapStateToProps
    0.48
    zewod
    0.48
    Controllo
    0.47
     Esprit
    0.46
    Activations Density 0.003%

    No Known Activations