© 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. 5-CLT-HP
    7. 96766
    Prev
    Next
    INDEX
    Explanations

    News and personal stories

    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
    COUVER
    -0.66
     me
    -0.59
     autorytatywna
    -0.58
    Vidite
    -0.55
     learned
    -0.55
    Abitanti
    -0.54
    addCriterion
    -0.52
     micro
    -0.52
    द्धि
    -0.50
     looked
    -0.50
    POSITIVE LOGITS
     aveug
    0.73
     EconPapers
    0.72
     enfans
    0.69
     vermelhas
    0.69
     navideños
    0.68
     larmes
    0.67
     engraçadas
    0.65
    enumi
    0.63
     vœux
    0.63
     rekke
    0.62
    Activations Density 0.000%

    No Known Activations