© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97400
    Prev
    Next
    INDEX
    Explanations

    legal and academic texts

    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
    oose
    -1.36
     فريبيس
    -0.94
    +#+#
    -0.85
     виправивши
    -0.82
     JpaRepository
    -0.79
    NegativeButton
    -0.73
    RenderAtEndOf
    -0.73
    featureID
    -0.71
     rodea
    -0.71
    зулта
    -0.69
    POSITIVE LOGITS
     inter
    0.57
    ADVERTISEMENT
    0.56
    insics
    0.54
     Thessalon
    0.53
    sition
    0.51
     de
    0.48
     Inter
    0.47
    州市
    0.47
    pompa
    0.47
    Advertisement
    0.47
    Activations Density 0.170%

    No Known Activations