© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 343
    Prev
    Next
    INDEX
    Explanations

    Giving

    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
     autorytatywna
    -0.74
     estekak
    -0.67
     EconPapers
    -0.61
     nakalista
    -0.56
    thâu
    -0.51
     hillside
    -0.50
    arraycopy
    -0.50
     sessile
    -0.48
    tispiece
    -0.48
     valleys
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.59
    addFlags
    0.54
    tagHelperRunner
    0.54
     AppBundle
    0.51
    UpInside
    0.50
    entant
    0.49
     Мексичка
    0.49
     onData
    0.49
    WEBPACK
    0.48
     Houſe
    0.48
    Activations Density 0.003%

    No Known Activations