© 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. 0-CLT-HP
    7. 93006
    Prev
    Next
    INDEX
    Explanations

    ideal, perfect, optimal

    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
     perfect
    -1.40
     ideal
    -1.34
    ideal
    -1.24
    perfect
    -1.19
    Ideal
    -1.13
     Ideal
    -1.06
     optimal
    -1.01
    Perfect
    -0.99
     ideale
    -0.97
     Perfect
    -0.96
    POSITIVE LOGITS
     ddelweddau
    0.73
    djangoproject
    0.72
     UITableViewCell
    0.63
     opérateur
    0.62
    nodoc
    0.61
    erweise
    0.57
    XMLSchema
    0.56
    Zunanje
    0.56
     Normdatei
    0.56
    ногда
    0.55
    Activations Density 0.039%

    No Known Activations