© 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. 2687
    Prev
    Next
    INDEX
    Explanations

    prefixes

    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
    ukone
    -0.61
     recovered
    -0.60
     baseman
    -0.54
    ErrUnexpectedEOF
    -0.52
     compleanno
    -0.51
    Aholisi
    -0.51
     riuscito
    -0.50
    BlockingQueue
    -0.50
    principalColumn
    -0.49
     successo
    -0.49
    POSITIVE LOGITS
    enterOuterAlt
    0.60
    history
    0.57
    __":
    0.54
    
    0.53
     history
    0.51
    Reactivity
    0.51
    னை
    0.50
    Portály
    0.49
    brainly
    0.48
    :✨
    0.48
    Activations Density 0.001%

    No Known Activations