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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96831
    Prev
    Next
    INDEX
    Explanations

    ability

    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
    Solución
    -0.56
     المعيارى
    -0.54
    ErrUnexpectedEOF
    -0.49
     meur
    -0.49
     olvides
    -0.47
    flower
    -0.45
    pherds
    -0.44
     typelib
    -0.44
    ORAGE
    -0.44
    ksom
    -0.44
    POSITIVE LOGITS
    manjaro
    0.65
     MainAxisSize
    0.58
    archiviato
    0.54
    unicaciones
    0.52
     winner
    0.51
     victor
    0.49
     Xanth
    0.49
    weigh
    0.49
     weighing
    0.49
    ipot
    0.48
    Activations Density 0.000%

    No Known Activations