© 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. 91016
    Prev
    Next
    INDEX
    Explanations

    settlement

    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
     settlements
    -1.27
     Settlements
    -1.24
     settlement
    -1.01
     SETTLE
    -1.00
    Settlement
    -0.99
    settlement
    -0.99
    Settle
    -0.96
     Settlement
    -0.95
    settle
    -0.94
    #+#
    -0.78
    POSITIVE LOGITS
    es
    0.57
    t
    0.54
    ts
    0.53
    eval
    0.53
    i
    0.51
    ta
    0.48
    g
    0.48
     convi
    0.47
    e
    0.47
    a
    0.47
    Activations Density 0.075%

    No Known Activations