© 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. 1-CLT-HP
    7. 9469
    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
     consultato
    -0.72
    脚注の使い方
    -0.62
     tan
    -0.42
    ep
    -0.42
    AccessorTable
    -0.42
    addPreferredGap
    -0.40
    god
    -0.40
    ab
    -0.40
    happy
    -0.40
    AfterClass
    -0.40
    POSITIVE LOGITS
     itſelf
    0.90
     Majefty
    0.68
     himſelf
    0.68
     myſelf
    0.67
     ſta
    0.66
     poffe
    0.66
     Efq
    0.65
     Jefus
    0.65
     raiſ
    0.65
    ыгана
    0.63
    Activations Density 0.004%

    No Known Activations