© 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. 1-CLT-HP
    7. 13072
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
     are
    -0.92
     vannak
    -0.84
     ARE
    -0.80
    ScopeManager
    -0.79
     were
    -0.78
     aren
    -0.77
     WERE
    -0.77
    Are
    -0.75
    were
    -0.75
    makeConstraints
    -0.74
    POSITIVE LOGITS
     is
    1.32
     has
    1.01
     does
    0.99
     was
    0.90
     doesn
    0.88
     isn
    0.82
     takes
    0.80
     offers
    0.79
     hasn
    0.78
     plays
    0.78
    Activations Density 0.206%

    No Known Activations