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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43087
    Prev
    Next
    INDEX
    Explanations

    fighter

    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
    Defense
    -1.07
     defense
    -1.04
     Defense
    -0.99
    fighting
    -0.98
     defending
    -0.97
     defensively
    -0.96
     acting
    -0.93
    fighter
    -0.92
     Fighter
    -0.92
     defenses
    -0.90
    POSITIVE LOGITS
     substrate
    0.51
    !("{
    0.48
     substrates
    0.48
    intan
    0.47
     OFDb
    0.46
     pulse
    0.45
     vendor
    0.44
     function
    0.43
     الدولى
    0.43
     train
    0.43
    Activations Density 0.322%

    No Known Activations