© 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. 0-CLT-HP
    7. 42372
    Prev
    Next
    INDEX
    Explanations

    gospel, renaming, indoor

    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
     gospel
    -2.02
     Gospel
    -1.81
    Gospel
    -1.42
    adaptiveStyles
    -0.88
    ospel
    -0.86
     مرئيه
    -0.85
    AccessorTable
    -0.84
    دانشنامهٔ
    -0.84
     Evangelio
    -0.79
     église
    -0.76
    POSITIVE LOGITS
     kasarigan
    0.61
     account
    0.54
     image
    0.51
    localctx
    0.50
     appearance
    0.49
     tr
    0.46
     piece
    0.46
    -
    0.46
     statement
    0.45
     land
    0.44
    Activations Density 0.416%

    No Known Activations