© 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. 92138
    Prev
    Next
    INDEX
    Explanations

    current events and progress

    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
    -0.81
     occaf
    -0.70
     fevere
    -0.68
     Efq
    -0.68
     ſtate
    -0.64
     ftate
    -0.62
    ्म
    -0.62
     poffe
    -0.60
     contingencies
    -0.60
     bershka
    -0.58
    POSITIVE LOGITS
    曖昧さ回避
    0.74
    enumi
    0.72
    تقاوى
    0.68
     pinulongan
    0.65
    UnsafeEnabled
    0.64
    SharedDtor
    0.63
     estimés
    0.60
     <>",
    0.56
    WithIOException
    0.56
     disponibilités
    0.55
    Activations Density 0.239%

    No Known Activations