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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40101
    Prev
    Next
    INDEX
    Explanations

    shear or prayer

    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
     prayer
    -0.81
     themſelves
    -0.75
     ſind
    -0.73
     Theſe
    -0.72
    prayer
    -0.72
     himſelf
    -0.70
     purpoſe
    -0.70
     pray
    -0.70
     Prayer
    -0.69
     Reſ
    -0.69
    POSITIVE LOGITS
    ist
    0.94
    id
    0.71
    ists
    0.67
    ,
    0.67
    i
    0.65
    tr
    0.63
     (
    0.63
    z
    0.61
    mat
    0.60
    r
    0.60
    Activations Density 0.084%

    No Known Activations