© 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. 44197
    Prev
    Next
    INDEX
    Explanations

    policies

    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
     policies
    -1.78
    policies
    -1.52
     Policies
    -1.49
     POLICIES
    -1.40
    Policies
    -1.34
    ITERATURE
    -0.82
    IBLIO
    -0.81
     }}"></
    -0.79
     politiques
    -0.78
     photolibrary
    -0.77
    POSITIVE LOGITS
     that
    0.54
     (
    0.47
     >=",
    0.45
     and
    0.43
     That
    0.42
     er
    0.41
    RegressionTest
    0.40
    ngiliz
    0.40
     بيها
    0.40
    tabilis
    0.40
    Activations Density 0.067%

    No Known Activations