© 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. 5-CLT-HP
    7. 97415
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     المعيارى
    -0.60
    enumi
    -0.52
    cookieParser
    -0.51
     taille
    -0.48
    RefreshLayout
    -0.48
     EventEmitter
    -0.48
    ractable
    -0.48
     svar
    -0.48
    sivi
    -0.47
    értelmű
    -0.47
    POSITIVE LOGITS
     مشين
    0.74
     ویکی‌پدی
    0.65
    MigrationBuilder
    0.62
     defaultstate
    0.59
    fromnode
    0.59
     nawr
    0.57
    foil
    0.56
    kháu
    0.54
    "]));
    0.53
    Biographie
    0.52
    Activations Density 0.002%

    No Known Activations