© 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. 4-CLT-HP
    7. 3146
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    woke
    -0.48
    ie
    -0.48
     woke
    -0.46
    rungsseite
    -0.45
    終わった
    -0.43
    
    -0.43
    selling
    -0.43
     proceeded
    -0.41
    cita
    -0.41
    hamed
    -0.41
    POSITIVE LOGITS
     ISNI
    0.73
     disponibilités
    0.65
    makeText
    0.63
    DataAnnotations
    0.61
     Sabha
    0.60
     kohdetta
    0.60
    tonsoft
    0.59
    ftagPool
    0.59
    ToBounds
    0.58
     getItemId
    0.57
    Activations Density 0.004%

    No Known Activations