© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97426
    Prev
    Next
    INDEX
    Explanations

    group/groups

    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
     مرئيه
    -1.09
     AssemblyCulture
    -1.07
     snippetHide
    -0.93
     ujednoznacz
    -0.92
    GEBURTSDATUM
    -0.92
    crollView
    -0.86
    IntoConstraints
    -0.82
    Personensuche
    -0.81
    WebElementEntity
    -0.80
     NSCoder
    -0.80
    POSITIVE LOGITS
     it
    0.49
     can
    0.47
    '
    0.43
    ’
    0.42
     like
    0.41
     suing
    0.41
    think
    0.40
    DataSnapshot
    0.40
    yecek
    0.39
     Think
    0.38
    Activations Density 0.043%

    No Known Activations