© 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. 4767
    Prev
    Next
    INDEX
    Explanations

    Symbols

    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
     betweenstory
    -0.86
     дописавши
    -0.83
    parsedMessage
    -0.79
     propOrder
    -0.74
    GEBURTSDATUM
    -0.71
    Parcelize
    -0.70
    UnifiedTopology
    -0.69
    archiviato
    -0.67
    grà
    -0.66
    Personendaten
    -0.66
    POSITIVE LOGITS
     répon
    0.55
    IIA
    0.45
    nių
    0.45
     bajas
    0.43
     alfombra
    0.42
    apor
    0.42
    ornis
    0.41
     moeite
    0.41
    bnb
    0.41
     gezicht
    0.41
    Activations Density 0.001%

    No Known Activations