© 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. 5-CLT-HP
    7. 98058
    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
    SharedDtor
    -0.44
    defer
    -0.42
     worship
    -0.41
    O
    -0.41
     closeness
    -0.40
     thanking
    -0.39
    CloseOperation
    -0.39
    Recognition
    -0.38
    Respect
    -0.38
     gratitude
    -0.38
    POSITIVE LOGITS
    ContentAsync
    0.79
    Personensuche
    0.69
    ="<?=
    0.69
     متعلقه
    0.68
    #+#
    0.66
    ReusableCell
    0.66
     otomatig
    0.65
     actionPerformed
    0.65
     ModelExpression
    0.65
    ]]:
    0.65
    Activations Density 0.001%

    No Known Activations