© 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. 5-CLT-HP
    7. 2187
    Prev
    Next
    INDEX
    Explanations

    SS

    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
     surla
    -0.62
     AssemblyTitle
    -0.60
    ]=-
    -0.55
     EClass
    -0.55
    gól
    -0.52
     ناز
    -0.52
     astore
    -0.52
    #+#
    -0.51
     indisponible
    -0.51
     fört
    -0.51
    POSITIVE LOGITS
     Great
    0.56
    Great
    0.51
    ModelSerializer
    0.49
     United
    0.44
    Климат
    0.44
    ThroughAttribute
    0.43
    corrhi
    0.43
    gr
    0.43
     Bureau
    0.42
    T
    0.42
    Activations Density 0.013%

    No Known Activations