© 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. 0-CLT-HP
    7. 43982
    Prev
    Next
    INDEX
    Explanations

    cottage

    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
     Inca
    -1.41
    scale
    -0.62
     inca
    -0.58
    >{@
    -0.55
    show
    -0.52
    shaft
    -0.51
    GRANTED
    -0.49
    DoubleQuotes
    -0.49
     transfieras
    -0.49
     enseña
    -0.49
    POSITIVE LOGITS
    getSystemService
    0.60
     كومونز
    0.56
    кономі
    0.55
    rzost
    0.51
    paksa
    0.50
    doria
    0.50
    IBarButtonItem
    0.50
    Източници
    0.50
    limus
    0.50
     ')[
    0.50
    Activations Density 0.102%

    No Known Activations