© 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. 1-CLT-HP
    7. 45879
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    noinspection
    -0.54
     configureStore
    -0.47
    ngrx
    -0.43
     expend
    -0.43
    GetAxis
    -0.40
    ConfigService
    -0.39
     StringField
    -0.39
    世界杯
    -0.39
     onOptions
    -0.38
     getItemId
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.99
    AndEndTag
    0.95
     Italijani
    0.66
    thâu
    0.62
    Cyfeiriadau
    0.59
    endphp
    0.59
    XmlAccessType
    0.57
    awtextra
    0.56
    classnames
    0.56
    onViewCreated
    0.55
    Activations Density 0.021%

    No Known Activations