© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3674
    Prev
    Next
    INDEX
    Explanations

    pamph

    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
     varandra
    -0.68
    The
    -0.64
     utanför
    -0.62
     pouvoirs
    -0.59
     långt
    -0.59
    tså
    -0.58
     zichzelf
    -0.57
     större
    -0.56
    It
    -0.56
     huden
    -0.56
    POSITIVE LOGITS
    PerformLayout
    0.59
    rungsseite
    0.54
    Geplaatst
    0.54
    astéroïdes
    0.53
     mantis
    0.53
     kasarigan
    0.52
     ostavi
    0.52
    saurus
    0.51
     تضيفلها
    0.50
    addCriterion
    0.50
    Activations Density 0.003%

    No Known Activations