© 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. 90561
    Prev
    Next
    INDEX
    Explanations

    code/math expressions

    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
    ddots
    -0.48
    queryInterface
    -0.44
    OGND
    -0.44
    ulic
    -0.42
    ialmente
    -0.42
     Great
    -0.41
    nak
    -0.41
    mones
    -0.41
    Lugares
    -0.41
    Transactional
    -0.41
    POSITIVE LOGITS
     otomatig
    0.74
    期刊论文
    0.72
    KommentareTeilen
    0.71
     resourceCulture
    0.68
    \{\\
    0.68
    Geplaatst
    0.66
    üyada
    0.60
    StructEnd
    0.60
    发表于
    0.59
     AppDelegate
    0.59
    Activations Density 0.097%

    No Known Activations