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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92194
    Prev
    Next
    INDEX
    Explanations

    repeating patterns/rules

    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
     Majefty
    -0.57
    gameserver
    -0.51
    ſelves
    -0.49
    ſelf
    -0.49
     Saltar
    -0.48
    Thir
    -0.48
     frequency
    -0.47
     iſt
    -0.47
     pracov
    -0.46
     Hift
    -0.45
    POSITIVE LOGITS
    EndContext
    0.73
     متعلقه
    0.71
     pageContext
    0.70
     Chwiliwch
    0.69
     SwitchCompat
    0.66
    ParallelGroup
    0.65
     CreateTagHelper
    0.65
    SequentialGroup
    0.65
    PhysRev
    0.65
    awtextra
    0.63
    Activations Density 0.059%

    No Known Activations