© 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. 4-CLT-HP
    7. 4392
    Prev
    Next
    INDEX
    Explanations

    code, file paths

    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
    uette
    -0.50
    Демографія
    -0.48
     MB
    -0.47
    Autoritní
    -0.46
    monių
    -0.46
    MV
    -0.46
    MQ
    -0.45
    MB
    -0.45
    illips
    -0.44
    imdi
    -0.44
    POSITIVE LOGITS
     to
    0.80
    fromCharCode
    0.68
     BorderRadius
    0.68
     nakalista
    0.65
    WebServlet
    0.63
     NSCoder
    0.63
    ChildScrollView
    0.59
     MainAxisSize
    0.58
     FileWriter
    0.56
    imedia
    0.56
    Activations Density 0.006%

    No Known Activations