© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41665
    Prev
    Next
    INDEX
    Explanations

    conflict

    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
     conflict
    -2.02
     Conflict
    -1.86
    conflict
    -1.73
     conflicts
    -1.71
    Conflict
    -1.63
     Conflicts
    -1.60
     conflicto
    -1.51
     dispute
    -1.38
     conflit
    -1.36
     conflits
    -1.35
    POSITIVE LOGITS
     between
    0.69
    detectChanges
    0.64
    SharedDtor
    0.63
     with
    0.61
    NameInMap
    0.59
    ant
    0.57
    Lähteet
    0.55
     zone
    0.53
     &___
    0.52
    parsedMessage
    0.52
    Activations Density 0.069%

    No Known Activations