© 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. 45096
    Prev
    Next
    INDEX
    Explanations

    external

    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
     external
    -1.92
     External
    -1.62
    external
    -1.47
    External
    -1.44
     outside
    -1.42
     externally
    -1.35
     Outside
    -1.31
    Outside
    -1.30
     EXTERNAL
    -1.27
    outside
    -1.26
    POSITIVE LOGITS
    InstanceState
    0.50
    InvalidProtocol
    0.49
     sentencing
    0.48
     webcam
    0.47
     disagreement
    0.46
     disagree
    0.45
     Chesapeake
    0.45
     defending
    0.44
     warfare
    0.44
     inferences
    0.44
    Activations Density 0.111%

    No Known Activations