© 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. 43509
    Prev
    Next
    INDEX
    Explanations

    research and evaluations

    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
     obligation
    -1.09
     Obligation
    -0.95
     institution
    -0.91
    obligation
    -0.87
     obliged
    -0.85
     oblige
    -0.85
     obligations
    -0.81
    EndContext
    -0.77
     Oblig
    -0.77
     Obligations
    -0.77
    POSITIVE LOGITS
    esModule
    0.57
    queda
    0.52
     rare
    0.51
     moral
    0.51
    igue
    0.50
    zerű
    0.50
    $}}
    0.50
    leur
    0.49
    addCriterion
    0.48
     isInitialized
    0.47
    Activations Density 0.113%

    No Known Activations