© 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. 4-CLT-HP
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    century

    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
     @"/
    -0.75
     nakalista
    -0.73
     EconPapers
    -0.73
    GraphicsUnit
    -0.73
    GEBURTSDATUM
    -0.67
    IsMutable
    -0.61
    省市镇
    -0.60
    ktop
    -0.60
     lenker
    -0.58
     Normdatei
    -0.58
    POSITIVE LOGITS
    రి
    0.51
    idosis
    0.49
    UrlResolution
    0.47
     Judaism
    0.46
     ADF
    0.46
    rawtypes
    0.45
    mox
    0.44
     armat
    0.44
    Luft
    0.43
     subprocess
    0.42
    Activations Density 0.003%

    No Known Activations