© 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. 97027
    Prev
    Next
    INDEX
    Explanations

    explanation, interpretation

    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
     explanation
    -0.91
     translate
    -0.88
    explanation
    -0.81
     interpretation
    -0.80
    interpretation
    -0.79
    pretation
    -0.73
    CELLANEOUS
    -0.73
     translation
    -0.71
     translates
    -0.68
    ICALS
    -0.67
    POSITIVE LOGITS
     estekak
    0.57
     pronti
    0.56
     of
    0.54
     ogen
    0.53
     özg
    0.50
     पे
    0.46
     Anexo
    0.45
    笠
    0.43
     végétale
    0.43
     material
    0.42
    Activations Density 0.077%

    No Known Activations