© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 594
    Prev
    Next
    INDEX
    Explanations

    religion/belief

    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
     belief
    -0.71
     believe
    -0.65
     croit
    -0.60
    belief
    -0.60
     believing
    -0.59
    Believe
    -0.59
    Belief
    -0.59
     creía
    -0.57
     glauben
    -0.56
     croire
    -0.55
    POSITIVE LOGITS
     متعلقه
    0.81
    GOTREF
    0.70
     CURIAM
    0.66
    fjspx
    0.65
     виправивши
    0.63
    RectangleBorder
    0.62
    writeFieldEnd
    0.61
    DeleteBehavior
    0.60
    sizeCache
    0.60
     Esau
    0.60
    Activations Density 0.011%

    No Known Activations