© 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. 1-CLT-HP
    4. 13111
    Prev
    Next
    INDEX
    Explanations

    tional

    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
    tional
    -1.93
    IONAL
    -1.21
    tionally
    -1.03
    tions
    -0.83
    ional
    -0.82
    tioned
    -0.80
    tion
    -0.73
    s
    -0.72
     tional
    -0.69
    ionale
    -0.60
    POSITIVE LOGITS
    __':
    
    0.80
    copg
    0.62
    tagext
    0.60
    "।
    0.59
    izing
    0.59
     Stead
    0.57
    WithIOException
    0.57
    abestanden
    0.56
    AutoresizingMask
    0.56
    IndentedString
    0.56
    Activations Density 0.025%

    No Known Activations