© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94827
    Prev
    Next
    INDEX
    Explanations

    scientific

    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
     Scientific
    -2.02
    Scientific
    -1.95
     SCIENTIFIC
    -1.88
     scientific
    -1.82
    scientific
    -1.73
     scientifically
    -1.59
     scientifique
    -1.45
     científico
    -1.40
     científica
    -1.36
     scientifiques
    -1.27
    POSITIVE LOGITS
    ally
    1.26
    ALLY
    0.92
    s
    0.85
    ity
    0.78
    ات
    0.56
    als
    0.54
    itys
    0.54
    ality
    0.50
    ITY
    0.49
    ים
    0.48
    Activations Density 0.202%

    No Known Activations