© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45626
    Prev
    Next
    INDEX
    Explanations

    rail

    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
     rail
    -0.87
    rail
    -0.84
     Rail
    -0.74
     RAIL
    -0.73
     rails
    -0.69
    Rail
    -0.64
    rails
    -0.59
    abestanden
    -0.56
    RAIL
    -0.56
    er
    -0.55
    POSITIVE LOGITS
    FieldNumber
    0.60
    
    0.60
     Jurí
    0.56
    coroutines
    0.54
    ่านั้น
    0.52
     unbekannt
    0.51
    cetin
    0.50
    ledad
    0.50
    autique
    0.50
    WebControls
    0.50
    Activations Density 0.057%

    No Known Activations