© 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. 5-CLT-HP
    4. 997
    Prev
    Next
    INDEX
    Explanations

    programming and technical context

    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
     fork
    -0.36
     freg
    -0.35
     equally
    -0.34
     excessively
    -0.34
     impea
    -0.31
     собой
    -0.31
     fawn
    -0.30
    ESS
    -0.30
     sprung
    -0.30
     widely
    -0.29
    POSITIVE LOGITS
     tartalomajánló
    1.05
    '},
    
    0.97
    '})
    0.93
    تقاوى
    0.93
    '}}
    0.89
     mergeFrom
    0.88
    '}),
    0.87
    invokeLater
    0.84
     beginnetje
    0.84
    }")]
    0.84
    Activations Density 0.013%

    No Known Activations