© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91953
    Prev
    Next
    INDEX
    Explanations

    Online comments/text snippets

    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
    ANT
    -0.72
    y
    -0.62
    o
    -0.59
    lau
    -0.57
    s
    -0.57
     ANT
    -0.56
    a
    -0.55
     Comments
    -0.54
    sana
    -0.52
    BagConstraints
    -0.51
    POSITIVE LOGITS
    出版年
    0.67
    ässe
    0.66
    BibitemShut
    0.65
    QMetaType
    0.63
     AssemblyCulture
    0.61
    SEGUIR
    0.60
    etheless
    0.59
    ✨:
    0.57
    Lähteet
    0.56
    nessed
    0.56
    Activations Density 0.129%

    No Known Activations