© 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. 5-CLT-HP
    7. 94967
    Prev
    Next
    INDEX
    Explanations

    religion

    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
    ThroughAttribute
    -0.66
     ExecuteAsync
    -0.66
    GEBURTSDATUM
    -0.63
    WithIOException
    -0.62
     Inspired
    -0.62
    remo
    -0.56
    intios
    -0.53
    hup
    -0.53
    Inspired
    -0.53
    ings
    -0.53
    POSITIVE LOGITS
    Autoritní
    0.53
    
    0.48
     المعرف
    0.45
    Hochspringen
    0.44
    aronder
    0.43
    plaque
    0.42
     sige
    0.42
    jsii
    0.39
     residency
    0.39
     afterward
    0.38
    Activations Density 0.030%

    No Known Activations