© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    resident

    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
     resident
    -0.82
    resident
    -0.71
    Rhestr
    -0.70
     citizen
    -0.68
    twimg
    -0.66
    letoe
    -0.65
     volume
    -0.65
     inhabitant
    -0.63
    \{\\
    -0.63
     pupil
    -0.62
    POSITIVE LOGITS
    fjspx
    0.52
     AssemblyTitle
    0.47
    حياتها
    0.47
     who
    0.47
    seamnă
    0.43
    InjectAttribute
    0.41
    etCode
    0.40
     căr
    0.40
    Condol
    0.40
    SpringBootTest
    0.40
    Activations Density 0.001%

    No Known Activations