© 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. 1-CLT-HP
    7. 716
    Prev
    Next
    INDEX
    Explanations

    Formal/academic language

    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
    <bos>
    -1.38
     whilst
    -0.64
    Whilst
    -0.55
     Whilst
    -0.49
    ´
    -0.47
     utilising
    -0.46
     favour
    -0.45
     totalling
    -0.44
     favours
    -0.44
     likely
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.80
     feroit
    0.78
     JpaRepository
    0.73
    TagMode
    0.72
     prestazioni
    0.71
     varandra
    0.70
     médec
    0.69
    ArgsConstructor
    0.69
     amitié
    0.68
     auroit
    0.67
    Activations Density 0.928%

    No Known Activations