© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74930
    Prev
    Next
    INDEX
    Explanations

    states

    np_max-act-logits · 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
    MessageTagHelper
    -0.73
    IntoConstraints
    -0.65
    ValueGeneration
    -0.64
    ViewImports
    -0.61
    脚注の使い方
    -0.60
    DoubleQuotes
    -0.57
    copg
    -0.56
    }));
    -0.56
     समीक्षक
    -0.55
    extAlignment
    -0.55
    POSITIVE LOGITS
     states
    0.76
    states
    0.67
    LookAnd
    0.66
    functions
    0.62
     products
    0.59
    products
    0.58
     functions
    0.56
     forces
    0.56
     States
    0.54
     STATES
    0.54
    Activations Density 0.001%

    No Known Activations