© 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. 43490
    Prev
    Next
    INDEX
    Explanations

    distracting

    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
     démocr
    -1.27
     avoient
    -1.18
     énergé
    -1.17
     étoient
    -1.17
     auroit
    -1.16
     feroit
    -1.15
     ſeveral
    -1.14
     itſelf
    -1.14
     larmes
    -1.13
     traités
    -1.13
    POSITIVE LOGITS
    s
    1.23
    ly
    1.17
     op
    0.69
     par
    0.67
    sing
    0.66
    ی
    0.65
     di
    0.65
    sr
    0.64
    y
    0.63
    ы
    0.63
    Activations Density 0.191%

    No Known Activations