© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40344
    Prev
    Next
    INDEX
    Explanations

    legal/military context

    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
     chance
    -1.41
     defense
    -1.41
     defence
    -1.27
     Defense
    -1.21
    Defense
    -1.17
    defense
    -1.16
     DEFENSE
    -1.12
     Chance
    -1.10
    chance
    -1.09
     Execution
    -1.08
    POSITIVE LOGITS
    s
    0.58
    mills
    0.49
    brite
    0.49
    anera
    0.47
    |}{$
    0.46
     majeure
    0.45
    a
    0.45
    y
    0.45
    sor
    0.44
    keeping
    0.43
    Activations Density 0.121%

    No Known Activations