© 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. 97320
    Prev
    Next
    INDEX
    Explanations

    followed

    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
     
    -0.58
    ↵↵
    -0.54
     indépendante
    -0.52
     habituales
    -0.49
     proposées
    -0.49
     contratos
    -0.46
     relojes
    -0.46
     "
    -0.46
     actuelles
    -0.46
     independientes
    -0.45
    POSITIVE LOGITS
     resourceCulture
    1.09
    Personendaten
    1.06
     Efq
    1.03
     Theſe
    1.01
    DockStyle
    1.00
    BufferException
    0.98
    DoubleQuotes
    0.98
    ArgsConstructor
    0.98
     Anſ
    0.97
     doubtnut
    0.97
    Activations Density 0.973%

    No Known Activations