Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 98288
    Prev
    Next
    INDEX
    Explanations

    Descriptive, subjective language

    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
    tagHelperRunner
    -1.07
    CloseOperation
    -0.95
    ंदीखरीदारी
    -0.93
    :✨
    -0.92
     otomatig
    -0.91
     Efq
    -0.91
    ValueStyle
    -0.88
    ThroughAttribute
    -0.87
    GEBURTSDATUM
    -0.85
    NameInMap
    -0.83
    POSITIVE LOGITS
     and
    0.51
     imp
    0.50
    -
    0.47
     im
    0.45
     informed
    0.44
    .
    0.44
    ,
    0.42
     to
    0.42
     of
    0.42
     displayed
    0.41
    Activations Density 0.075%

    No Known Activations