© 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. 5-CLT-HP
    7. 94594
    Prev
    Next
    INDEX
    Explanations

    .

    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
     समीक्षक
    -0.76
    ьаж
    -0.72
    ViewFeatures
    -0.72
     المعيارى
    -0.70
    Sucesor
    -0.70
     iconFacebook
    -0.66
    expandindo
    -0.65
     nahilalakip
    -0.65
     Wikimedijinoj
    -0.65
    UnsafeEnabled
    -0.65
    POSITIVE LOGITS
     Avignon
    0.49
    ,-\
    0.48
    msgid
    0.47
     Warszaw
    0.47
     keyring
    0.45
    بالإنجليزية
    0.44
    TypedDataSet
    0.44
     zależy
    0.44
    PLE
    0.42
     extran
    0.42
    Activations Density 0.004%

    No Known Activations