© 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. 40118
    Prev
    Next
    INDEX
    Explanations

    gathering, spreading

    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
     Accesat
    -0.57
     successful
    -0.56
    successful
    -0.47
    uric
    -0.47
     invokingState
    -0.45
     būs
    -0.43
     IATA
    -0.42
     čierna
    -0.42
     Domini
    -0.41
    spoken
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
     betweenstory
    0.66
     kasarigan
    0.66
    ########.
    0.65
    mybatisplus
    0.63
    Rhestr
    0.56
     odb
    0.56
    ValueStyle
    0.54
    kuuta
    0.54
    derabad
    0.54
    Activations Density 0.119%

    No Known Activations