© 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. 38674
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific texts

    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
    er
    -0.63
    en
    -0.55
    fulness
    -0.52
    ter
    -0.50
    ه
    -0.47
    tors
    -0.47
    o
    -0.46
    or
    -0.46
    es
    -0.46
    chik
    -0.45
    POSITIVE LOGITS
    TypedDataSet
    0.78
    PyExc
    0.76
     surla
    0.73
     disambiguazione
    0.72
    сылкі
    0.71
     kaarangay
    0.70
    OGND
    0.68
     الحره
    0.68
     pleaſure
    0.68
     Administrativna
    0.66
    Activations Density 0.220%

    No Known Activations