© 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. 4-CLT-HP
    7. 1665
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ChildScrollView
    -0.85
     lenker
    -0.72
     Roskov
    -0.65
    medriver
    -0.65
     فريبيس
    -0.64
    crollView
    -0.62
    UnsafeEnabled
    -0.60
    jooq
    -0.58
     StatelessWidget
    -0.57
    UnifiedTopology
    -0.56
    POSITIVE LOGITS
    saraba
    0.73
     مشين
    0.59
     added
    0.58
    Added
    0.56
     additional
    0.56
     aggiun
    0.56
    Carriera
    0.52
     habilidad
    0.50
    __);
    0.50
     possible
    0.50
    Activations Density 0.012%

    No Known Activations