© 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. 0-CLT-HP
    7. 97659
    Prev
    Next
    INDEX
    Explanations

    referred

    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
     called
    -1.00
     referred
    -0.85
    referred
    -0.68
     CALLED
    -0.64
    called
    -0.63
    Called
    -0.60
     llamada
    -0.59
     named
    -0.57
     Called
    -0.57
     bursting
    -0.54
    POSITIVE LOGITS
     AssemblyTitle
    0.73
    ⓧ
    0.59
     beginnetje
    0.58
    Rhestr
    0.56
    ècie
    0.54
    Notae
    0.53
    Ashlee
    0.51
     informação
    0.51
     useEffect
    0.50
     pioggia
    0.49
    Activations Density 0.054%

    No Known Activations