© 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. 42677
    Prev
    Next
    INDEX
    Explanations

    literature

    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
     literature
    -1.05
     letteratura
    -0.96
     character
    -0.95
     Literature
    -0.91
     Character
    -0.91
     LITERATURE
    -0.87
     literary
    -0.83
    Literature
    -0.79
    character
    -0.77
     literatura
    -0.77
    POSITIVE LOGITS
     ExecuteAsync
    0.66
    ksikon
    0.58
     <=",
    0.54
    ⓧ
    0.54
    roidery
    0.54
    onViewCreated
    0.53
     Noah
    0.52
     autorytatywna
    0.51
    ContentLoaded
    0.50
    ⚐
    0.50
    Activations Density 0.159%

    No Known Activations