© 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. 4-CLT-HP
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    diseases

    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
     Treated
    -0.55
     interni
    -0.54
     treated
    -0.54
    tagHelperRunner
    -0.53
     consciences
    -0.52
     externi
    -0.50
    kasten
    -0.49
    treated
    -0.49
    Treat
    -0.48
     treats
    -0.47
    POSITIVE LOGITS
    MemoryWarning
    0.59
     convenient
    0.54
     Efq
    0.53
     @"/
    0.51
    rungsseite
    0.49
    曖昧さ回避
    0.49
    xically
    0.49
     NSCoder
    0.49
     safely
    0.48
    ]")]
    0.48
    Activations Density 0.027%

    No Known Activations