© 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. 0-CLT-HP
    4. 92088
    Prev
    Next
    INDEX
    Explanations

    code, legal documents

    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
    ⓧ
    -0.88
    StoryboardSegue
    -0.85
    Tikang
    -0.82
     autorytatywna
    -0.79
    PreferredItem
    -0.75
    elemField
    -0.69
     HasFactory
    -0.66
    ciclop
    -0.65
    ípios
    -0.64
    Gweler
    -0.63
    POSITIVE LOGITS
    "))
    
    0.52
    談社
    0.50
    }`)
    0.50
    }}}}
    0.50
    <>());
    0.49
    Revenir
    0.48
    }}}
    0.48
    ])
    
    0.48
    }`,
    0.46
    提出
    0.46
    Activations Density 1.631%

    No Known Activations