© 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. 1-CLT-HP
    7. 748
    Prev
    Next
    INDEX
    Explanations

    Evangelical, cyborg, apologetics

    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
     patriarchal
    -1.09
     Patriarch
    -0.72
     patriarch
    -0.64
     patri
    -0.55
     TextInputType
    -0.53
    ness
    -0.51
     []:
    -0.50
    withIdentifier
    -0.48
     journey
    -0.48
    ConstraintMaker
    -0.48
    POSITIVE LOGITS
     propOrder
    0.68
    uxxxx
    0.61
     dieux
    0.61
    ieteur
    0.59
     étr
    0.57
     églises
    0.55
     religieuses
    0.55
    براير
    0.54
     argint
    0.53
     sauvages
    0.52
    Activations Density 0.005%

    No Known Activations