© 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. 90716
    Prev
    Next
    INDEX
    Explanations

    tring

    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
    ividual
    -0.93
    uced
    -0.76
    __);
    -0.75
    ingar
    -0.74
    ️
    -0.74
    ematic
    -0.73
    ratulations
    -0.72
    arranty
    -0.72
    uthorized
    -0.70
    ymal
    -0.69
    POSITIVE LOGITS
    IsContent
    0.69
     ſte
    0.60
     Argentino
    0.59
    ISupport
    0.58
     Escolar
    0.57
    min
    0.56
     bershka
    0.55
     getItemId
    0.55
     tantum
    0.55
    my
    0.55
    Activations Density 0.077%

    No Known Activations