© 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. 1-CLT-HP
    4. 45837
    Prev
    Next
    INDEX
    Explanations

    depression and icons

    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
     depressed
    -1.02
     CreateTagHelper
    -0.82
     للمعارف
    -0.82
    PYX
    -0.66
    بوابة
    -0.61
    ffl
    -0.60
    /**
    -0.57
    <?
    -0.56
    jsk
    -0.56
     الحره
    -0.55
    POSITIVE LOGITS
    SequentialGroup
    0.55
     Tapatalk
    0.52
     astore
    0.46
    Butyl
    0.45
    altung
    0.45
     familiari
    0.45
    addLast
    0.45
    Varint
    0.44
     presta
    0.44
     Guerra
    0.44
    Activations Density 0.223%

    No Known Activations