© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94338
    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
    rungsseite
    -0.56
     препратки
    -0.54
    MigrationBuilder
    -0.53
     Use
    -0.50
    getSeconds
    -0.49
    èlement
    -0.49
    Gön
    -0.48
     bezeichneter
    -0.48
    ikor
    -0.48
    topf
    -0.48
    POSITIVE LOGITS
    awtextra
    0.68
     ویکی‌پدیا
    0.64
    InjectAttribute
    0.62
     aberto
    0.56
    XmlAccessorType
    0.56
    avaient
    0.56
    findpost
    0.55
    eseorang
    0.54
     sanitarias
    0.53
    راضي
    0.52
    Activations Density 0.002%

    No Known Activations