© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1119
    Prev
    Next
    INDEX
    Explanations

    Priority and citizens

    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
     citizen
    -0.96
    citizen
    -0.94
     Citizen
    -0.89
     ویکی‌پدیای
    -0.88
    Citizen
    -0.85
     citoyen
    -0.84
     صوتيه
    -0.81
    دانشنامهٔ
    -0.80
     citoy
    -0.78
    LookAnd
    -0.78
    POSITIVE LOGITS
     of
    0.71
     and
    0.66
    s
    0.64
    e
    0.58
     ca
    0.56
     Ca
    0.56
     running
    0.55
     In
    0.54
    .
    0.52
    ist
    0.52
    Activations Density 0.019%

    No Known Activations