© 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. 43146
    Prev
    Next
    INDEX
    Explanations

    battle

    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
     battle
    -1.81
     fight
    -1.48
    battle
    -1.43
     Battle
    -1.23
     battles
    -1.20
    Battle
    -1.17
     BATTLE
    -1.14
     battled
    -1.10
     batalla
    -1.04
     battling
    -1.04
    POSITIVE LOGITS
    awtextra
    0.73
     doInBackground
    0.60
    AndEndTag
    0.60
    ($__
    0.55
    NameInMap
    0.54
    Hauptartikel
    0.54
    ::::::::
    0.51
    able
    0.51
    
    0.47
     Besøkt
    0.44
    Activations Density 0.033%

    No Known Activations