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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1651
    Prev
    Next
    INDEX
    Explanations

    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
    .
    -0.57
     within
    -0.53
     examples
    -0.50
     newspapers
    -0.50
     pedestal
    -0.49
    inians
    -0.49
     in
    -0.48
     plainly
    -0.48
    abal
    -0.48
     instances
    -0.47
    POSITIVE LOGITS
    الحياه
    0.99
    <bos>
    0.84
    ftagPool
    0.84
    InjectAttribute
    0.77
     föruts
    0.73
    PYX
    0.68
    RegistryLite
    0.67
     оригіналу
    0.62
     hjär
    0.60
    ')],
    0.60
    Activations Density 0.003%

    No Known Activations