© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    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
    up
    -0.78
     persistent
    -0.65
    persistent
    -0.60
     Persistent
    -0.60
     persistently
    -0.56
    Persistent
    -0.56
    culature
    -0.56
    resolved
    -0.51
    assment
    -0.49
    ltä
    -0.49
    POSITIVE LOGITS
    expandindo
    0.91
     Efq
    0.85
     myſelf
    0.83
     Monfieur
    0.83
     itſelf
    0.83
     Jefus
    0.82
    tagHelperRunner
    0.81
     Eſ
    0.81
     defaultstate
    0.78
    parsedMessage
    0.78
    Activations Density 1.604%

    No Known Activations