© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    religious themes and blessings

    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
     endregion
    -0.54
     âgées
    -0.54
     légère
    -0.53
     étranger
    -0.52
     puissent
    -0.52
     précie
    -0.52
     connues
    -0.52
     puisse
    -0.51
     réguli
    -0.51
     citoy
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.70
     SafeMath
    0.57
    TagMode
    0.56
    esgue
    0.54
    ecap
    0.54
    ">//
    0.52
     Signalez
    0.52
    tréal
    0.52
     think
    0.51
     OnInit
    0.51
    Activations Density 0.003%

    No Known Activations