© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45487
    Prev
    Next
    INDEX
    Explanations

    Accessing systems or medicine

    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
    accessed
    -1.16
     accessed
    -0.94
    TypedDataSet
    -0.90
    berdayakan
    -0.90
     kasarigan
    -0.85
     GenerationType
    -0.84
     ویکی‌پدیا
    -0.83
    principalTable
    -0.82
    AndEndTag
    -0.82
     JpaRepository
    -0.81
    POSITIVE LOGITS
    a
    0.63
    i
    0.59
    ed
    0.58
    es
    0.57
    ing
    0.57
    ised
    0.48
    d
    0.48
    sed
    0.47
     us
    0.47
    ds
    0.46
    Activations Density 0.139%

    No Known Activations