© 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. 4-CLT-HP
    7. 3056
    Prev
    Next
    INDEX
    Explanations

    protection, safety, licensing

    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
     laikā
    -0.56
     reír
    -0.51
     ब्रेकडाउन
    -0.50
     européennes
    -0.48
     CHtml
    -0.47
    struzioni
    -0.47
     vecka
    -0.46
    TagMode
    -0.46
    openqa
    -0.46
     educativas
    -0.45
    POSITIVE LOGITS
     hopes
    0.98
     dreams
    0.94
     illusions
    0.86
     hope
    0.85
     fantasies
    0.78
    Personendaten
    0.78
    LookAnd
    0.75
     aspirations
    0.74
     ambitions
    0.72
     suspicions
    0.70
    Activations Density 0.001%

    No Known Activations