© 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. 38286
    Prev
    Next
    INDEX
    Explanations

    arches

    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
    s
    -0.82
    holds
    -0.69
    holding
    -0.69
    i
    -0.66
    ed
    -0.66
     a
    -0.61
     
    -0.61
    a
    -0.60
     j
    -0.52
    .
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    1.12
     متعلقه
    0.97
     '\\;'
    0.96
    enterOuterAlt
    0.91
    ValueGenerated
    0.91
     Anſ
    0.88
     ویکی‌پدی
    0.87
     unknownFields
    0.87
    DockStyle
    0.86
    يكب
    0.85
    Activations Density 0.965%

    No Known Activations