© 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. 2030
    Prev
    Next
    INDEX
    Explanations

    nearest

    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
     Савезне
    -1.41
    parsedMessage
    -1.30
     betweenstory
    -1.20
     للمعارف
    -1.19
     يتيمه
    -1.17
    EndInit
    -1.17
    IsContent
    -1.17
    TintMode
    -1.16
    oredCriteria
    -1.15
    :✨
    -1.09
    POSITIVE LOGITS
    <eos>
    0.80
    ↵↵
    0.61
    ↵
    0.55
    '
    0.54
    ’
    0.48
    \\
    0.46
    ↵↵↵
    0.44
    â
    0.44
    </strong>
    0.44
    one
    0.42
    Activations Density 0.310%

    No Known Activations