© 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. 94836
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ReusableCell
    -0.83
     فريبيس
    -0.80
     kasarigan
    -0.71
    TagMode
    -0.66
     gynhyrchwyd
    -0.66
     مرئيه
    -0.63
    AnimationsModule
    -0.63
    quelize
    -0.61
    LEncoder
    -0.61
    ParallelGroup
    -0.59
    POSITIVE LOGITS
     Khal
    0.43
     Fibonacci
    0.43
     somewhere
    0.43
    Espèce
    0.43
     heck
    0.42
     Heck
    0.41
     Puedes
    0.40
     anywhere
    0.40
    ecirc
    0.40
     inevit
    0.39
    Activations Density 0.000%

    No Known Activations